100 accepted papers
Deep sequence models are said to store atomic facts predominantly in the form of associative memory: a brute-force lookup of co-occurring entities. We identify a dramatically different form of storage of atomic facts that we term as geometric memory. Here, the model has synthesized embeddings encodi…
Parameter-Efficient Fine-Tuning (PEFT) strategies such as Low-Rank Adaptation (LoRA) are effective solutions for fine-tuning large-scale pre-trained models; however, their memory requirements scales with the size of the model, $\mathcal{O}(dr)$, where $d$ is the model's hidden dimension and $r$ is t…
Model routing is a simple technique for reducing the inference cost of large language models (LLMs), wherein one maintains a pool of candidate LLMs, and learns to route each prompt to the smallest feasible LLM. Existing works focus on learning a router for a fixed pool of LLMs. In this paper, we con…
Measuring similarity between training examples is critical for curating high-quality and diverse pretraining datasets for language models. However, similarity is typically computed with a generic off-the-shelf embedding model that has been trained for tasks such as retrieval. Whether these embeddi…
Decoder-based large language models (LLMs) have proven highly versatile, with remarkable successes even on problems ostensibly removed from traditional language generation. One such example is solving regression problems, where the targets are real numbers rather than textual tokens. A common appr…
Bipartite ranking is a fundamental supervised learning problem, with the goal of learning a ranking over instances with maximal area under the ROC curve (AUC) against a single binary target label. However, one may often observe multiple binary target labels, e.g., from distinct human annotators. How…
Recent developments in large language models have sparked interest in efficient pretraining methods. Stagewise training approaches to improve efficiency, like gradual stacking and layer dropping (Reddi et al., 2023; Zhang & He, 2020), have recently garnered attention. The prevailing view suggests th…
Cascades and speculative decoding are two common approaches to improving language models' inference efficiency. Both approaches interleave two models, but via fundamentally distinct mechanisms: deferral rule that invokes the larger model only for “hard” inputs, while speculative decoding uses spec…
Dual encoder (DE) models, where a pair of matching query and document are embedded into similar vector representations, are widely used in information retrieval due to their simplicity and scalability. However, the Euclidean geometry of the embedding space limits the expressive power of DEs, which m…
One of the core pillars of efficient deep learning methods are architectural improvements, such as residual/skip connections, which have led to significantly better model convergence and quality. Since their introduction, residual connections have become ubiquitous not only in convolutional neural n…
Low-rank adaption (LoRA) is a widely used parameter-efficient finetuning method for LLM that reduces memory requirements. However, current LoRA optimizers lack transformation invariance, meaning the updates depending on how the two LoRA factors are scaled or rotated. This deficiency leads to ineffic…
Large language models have shown remarkable reasoning abilities and scaling laws suggest that large parameter count, especially along the depth axis, is the primary driver. In this work, we make a stronger claim --- many reasoning problems require a large depth but not necessarily many parameters. T…
In-context Ranking (ICR) is an emerging paradigm for Information Retrieval (IR), which leverages contextual understanding of LLMs by directly incorporating the task description, candidate documents, and the query into the model's input prompt and tasking the LLM to identify relevant document(s). Whi…
The discovery of the *lazy neuron phenomenon* (Li et al., 2022), where fewer than 10% of the feedforward networks (FFN) parameters in trained Transformers are activated per token, has spurred significant interests in *activation sparsity* for enhancing large model efficiency. While notable progress…
We present a novel unified analysis for a broad class of adaptive optimization algorithms with structured (e.g., layerwise, diagonal, and kronecker-factored) preconditioners for both online regret minimization and offline convex optimization. Our analysis not only provides matching rate to several i…
Autoregressive language models have achieved remarkable advancements, yet their potential is often limited by the slow inference speeds associated with sequential token generation. Blockwise parallel decoding (BPD) was proposed by Stern et al. [42] as a method to improve inference speed of language…
Transformers to do reasoning and few-shot learning, without any fine-tuning, is widely conjectured to stem from their ability to implicitly simulate a multi-step algorithms -- such as gradient descent -- with their weights in a single forward pass. Recently, there has been progress in understanding…
Speculative decoding~(SD) accelerates large language model inference by employing a faster {\em draft} model for generating multiple tokens, which are then verified in parallel by the larger {\em target} model, resulting in the text generated according to the target model distribution. However, iden…
Preventing the performance decay of Transformers on inputs longer than those used for training has been an important challenge in extending the context length of these models. Though the Transformer architecture has fundamentally no limits on the input sequence lengths it can process, the choice of…
Recent advances in language models (LMs) have led to significant improvements in quality on complex NLP tasks, but at the expense of increased inference costs. A simple strategy to achieve more favorable cost-quality tradeoffs is cascading: here, a small model is invoked for most “easy” instances, w…
Learning to reject (L2R) is a classical problem where one seeks a classifier capable of abstaining on low-confidence samples. Most prior work on L2R has focused on minimizing the standard misclassification error. However, in many real-world applications, the label distribution is highly imbalanced,…
Modern text-to-image generation models produce high-quality images that are both photorealistic and faithful to the text prompts. However this quality comes at significant computational cost: nearly all of these models are iterative and require running sampling multiple times with large models. This…
Classical wisdom in machine learning holds that the generalization error can be decomposed into bias and variance, and these two terms exhibit a \emph{trade-off}. However, in this paper, we show that for an ensemble of deep learning based classification models, bias and variance are \emph{aligned} a…
Given the increasing scale of model sizes, efficient training strategies like gradual stacking have garnered interest. Stacking enables efficient training by gradually growing the depth of a model in stages and using layers from a smaller model in an earlier stage to initialize the next stage. Altho…
Real-world classifiers can benefit from the option of abstaining from predicting on samples where they have low confidence. Such abstention is particularly useful on samples which are close to the learned decision boundary, or which are outliers with respect to the training sample. These settings ha…
Autoregressive language models are the currently dominant paradigm for text generation, however they have some fundamental limitations that cannot be remedied by scale---for example inherently sequential and unidirectional generation. While alternate classes of models have been explored, we have lim…
Large language models (LLMs) have shown strong results on a range of applications, including regression and scoring tasks.Typically, one obtains outputs from an LLM via autoregressive sampling from the model’s output distribution. We show that this inference strategy can be sub-optimal for common re…
As with many machine learning problems the progress of image generation methods hinges on good evaluation metrics. One of the most popular is the Frechet Inception Distance (FID). FID estimates the distance between a distribution of Inception-v3 features of real images and those of images generated…
The autoregressive nature of conventional large language models (LLMs) inherently limits inference speed, as tokens are generated sequentially. While speculative (Leviathan et al., 2023) and parallel (Stern et al., 2018) decoding techniques attempt to mitigate this, they face limitations: either rel…
Language models generate responses by producing a series of tokens in immediate succession: the $(K+1)^{\rm th}$ token is an outcome of manipulating $K$ hidden vectors per layer, one vector per preceding token. What if instead we were to let the model manipulate say, $K+10$ hidden vectors, before it…
Pretrained large language models (LLMs) are general purpose problem solvers applicable to a diverse set of tasks with prompts. They can be further improved towards a specific task by fine-tuning on a specialized dataset. However, fine-tuning usually makes the model narrowly specialized on this datas…
Modern information retrieval (IR) systems consists of multiple stages like retrieval and ranking, with Transformer-based models achieving state-of-the-art performance at each stage. In this paper, we challenge the tradition of using separate models for different stages and ask if a single Transforme…
The approximate nearest neighbor (ANN) search problem is fundamental to efficiently serving many real-world machine learning applications. A number of techniques have been developed for ANN search that are efficient, accurate, and scalable. However, such techniques typically have a number of paramet…
Large deep learning models have achieved state-of-the-art performance across various natural language processing (NLP) tasks and demonstrated remarkable few-shot learning performance. However, training them is often challenging and resource-intensive. In this paper, we study an efficient approach to…
Large language models (LLMs) have led to a series of breakthroughs in natural language processing (NLP), partly owing to the massive amounts of world knowledge they memorize during pretraining. While many downstream applications provide the model with an informational context to aid its underlying t…
We present a subset selection algorithm designed to work with arbitrary model families in a practical batch setting. In such a setting, an algorithm can sample examples one at a time but, in order to limit overhead costs, is only able to update its state (i.e. further train model weights) once a lar…
Knowledge distillation (KD) has been widely used to improve the test accuracy of a "student" network, by training it to mimic the soft probabilities of a trained "teacher" network. Yet, it has been shown in recent work that, despite being trained to fit the teacher's probabilities, the student may n…
The impressive generalization performance of modern neural networks is attributed in part to their ability to implicitly memorize complex training patterns. Inspired by this, we explore a novel mechanism to improve model generalization via explicit memorization. Specifically, we propose the residual…
This paper introduces SOAR: **S**pilling with **O**rthogonality-**A**mplified **R**esiduals, a novel data indexing technique for approximate nearest neighbor (ANN) search. SOAR extends upon previous approaches to ANN search, such as spill trees, that utilize multiple redundant representations while…
Serving a GNN model online is challenging --- in many applications when testing nodes are connected to training nodes, one has to propagate information from training nodes to testing nodes to achieve the best performance, and storing the whole training set (including training graph and node features…
Despite the popularity and efficacy of knowledge distillation, there is limited understanding of why it helps. In order to study the generalization behavior of a distilled student, we propose a new theoretical framework that leverages supervision complexity: a measure of alignment between teacher-pr…
The remarkable performance gains realized by large pretrained models, e.g., GPT-3, hinge on the massive amounts of data they are exposed to during training. Analogously, distilling such large models to compact models for efficient deployment also necessitates a large amount of (labeled or unlabeled)…
This paper studies a curious phenomenon that machine learning model with Transformer architectures have sparse activation maps. By activation map we refer to the intermediate output of the multi-layer perceptrons (MLPs) after a ReLU activation function, and by "sparse" we mean that on average very f…
Cascades are a classical strategy to enable inference cost to vary adaptively across samples, wherein a sequence of classifiers are invoked in turn. A deferral rule determines whether to invoke the next classifier in the sequence, or to terminate prediction. One simple deferral rule employs the co…
Language models can be augmented with context retriever to incorporate knowledge from large external databases. By leveraging retrieved context, the neural network does not have to memorize the massive amount of world knowledge within its internal parameters, leading to better parameter efficiency,…
Transformer-based models such as BERT have proven successful in information retrieval problem, which seek to identify relevant documents for a given query. There are two broad flavours of such models: cross-attention (CA) models, which learn a joint embedding for the query and document, and dual-enc…
Many practical settings allow a learner to defer predictions to one or more costly experts. For example, the learning to defer paradigm allows a learner to defer to a human expert, at some monetary cost. Similarly, the adaptive inference paradigm allows a base model to defer to one or more large mod…
In contrast to SGD, adaptive gradient methods like Adam allow robust training of modern deep networks, especially large language models. However, the use of adaptivity not only comes at the cost of extra memory but also raises the fundamental question: can non-adaptive methods like SGD enjoy similar…
This paper presents a novel nearest neighbor search algorithm achieving TPU (Google Tensor Processing Unit) peak performance, outperforming state-of-the-art GPU algorithms with similar level of recall. The design of the proposed algorithm is motivated by an accurate accelerator performance model tha…
Knowledge distillation is a technique for improving a “student” model by replacing its one-hot training labels with a label distribution obtained from a “teacher” model. Despite its broad success, several basic questions — e.g., Why does distillation help? Why do more accurate teachers not necessari…
Federated learning is a distributed machine learning paradigm in which a large number of clients coordinate with a central server to learn a model without sharing their own training data. Standard federated optimization methods such as Federated Averaging (FedAvg) are often difficult to tune and exh…
The ability to train complex and highly effective models often requires an abundance of training data, which can easily become a bottleneck in cost, time, and computational resources. Batch active learning, which adaptively issues batched queries to a labeling oracle, is a common approach for addres…
The label shift problem refers to the supervised learning setting where the train and test label distributions do not match. Existing work addressing label shift usually assumes access to an unlabelled test sample. This sample may be used to estimate the test label distribution, and to then train a…
Negative sampling schemes enable efficient training given a large number of classes, by offering a means to approximate a computationally expensive loss function that takes all labels into account. In this paper, we present a new connection between these schemes and loss modification techniques for…
Factorized models, such as two tower neural network models, are widely used for scoring (query, document) pairs in information retrieval tasks. These models are typically trained by optimizing the model parameters to score relevant ``positive" pairs higher than the irrelevant ``negative" ones. While…
Feature based explanations, that provide importance of each feature towards the model prediction, is arguably one of the most intuitive ways to explain a model. In this paper, we establish a novel set of evaluation criteria for such feature based explanations by robustness analysis. In contrast to e…
Real-world classification problems typically exhibit an imbalanced or long-tailed label distribution, wherein many labels have only a few associated samples. This poses a challenge for generalisation on such labels, and also makes naive learning biased towards dominant labels. In this paper, we pr…
Overparameterised neural networks have demonstrated the remarkable ability to perfectly fit training samples, while still generalising to unseen test samples. However, several recent works have revealed that such models' good average performance does not always translate to good worst-case performan…
Knowledge distillation is an approach to improve the performance of a student model by using the knowledge of a complex teacher. Despite its success in several deep learning applications, the study of distillation is mostly confined to classification settings. In particular, the use of distillation…
Quantization based techniques are the current state-of-the-art for scaling maximum inner product search to massive databases. Traditional approaches to quantization aim to minimize the reconstruction error of the database points. Based on the observation that for a given query, the database points t…
Despite the widespread adoption of Transformer models for NLP tasks, the expressive power of these models is not well-understood. In this paper, we establish that Transformer models are universal approximators of continuous permutation equivariant sequence-to-sequence functions with compact support,…
Gradient clipping is a widely-used technique in the training of deep networks, and is generally motivated from an optimisation lens: informally, it controls the dynamics of iterates, thus enhancing the rate of convergence to a local minimum. This intuition has been made precise in a line of recent w…
Label smoothing is commonly used in training deep learning models, wherein one-hot training labels are mixed with uniform label vectors. Empirically, smoothing has been shown to improve both predictive performance and model calibration. In this paper, we study whether label smoothing is also effecti…
We consider learning a multi-class classification model in the federated setting, where each user has access to the positive data associated with only a single class. As a result, during each federated learning round, the users need to locally update the classifier without having access to the featu…
Neural Ordinary Differential Equation (Neural ODE) has been proposed as a continuous approximation to the ResNet architecture. Some commonly used regularization mechanisms in discrete neural networks (e.g., dropout, Gaussian noise) are missing in current Neural ODE networks. In this paper, we propos…
Training large deep neural networks on massive datasets is computationally very challenging. There has been recent surge in interest in using large batch stochastic optimization methods to tackle this issue. The most prominent algorithm in this line of research is LARS, which by employing layerwis…
Much of the literature on differential privacy focuses on item-level privacy, where loosely speaking, the goal is to provide privacy per item or training example. However, recently many practical applications such as federated learning require preserving privacy for all items of a single user, which…
In the learning to learn (L2L) framework, we cast the design of optimization algorithms as a machine learning problem and use deep neural networks to learn the update rules. In this paper, we extend the L2L framework to zeroth-order (ZO) optimization setting, where no explicit gradient information i…
Attention based Transformer architecture has enabled significant advances in the field of natural language processing. In addition to new pre-training techniques, recent improvements crucially rely on working with a relatively larger embedding dimension for tokens. Unfortunately, this leads to model…
Multi-stage training and knowledge transfer, from a large-scale pretraining task to various finetuning tasks, have revolutionized natural language processing and computer vision resulting in state-of-the-art performance improvements. In this paper, we develop a multi-stage influence function score…
Recently, Transformer networks have redefined the state of the art in many NLP tasks. However, these models suffer from quadratic computational cost in the input sequence length $n$ to compute pairwise attention in each layer. This has prompted recent research into sparse Transformers that sparsify…
We consider the large-scale query-document retrieval problem: given a query (e.g., a question), return the set of relevant documents (e.g., paragraphs containing the answer) from a large document corpus. This problem is often solved in two steps. The retrieval phase first reduces the solution space,…
Recently, there has been a surge of interest in representation learning in hyperbolic spaces, driven by their ability to represent hierarchical data with significantly fewer dimensions than standard Euclidean spaces. However, the viability and benefits of hyperbolic spaces for downstream machine lea…
We characterize the minimum noise amplitude and power for noise-adding mechanisms in (epsilon, delta)-differential privacy for single real-valued query function. We derive new lower bounds using the duality of linear programming, and new upper bounds by analyzing a special class of (epsilon, delta)-…
While stochastic gradient descent (SGD) is still the de facto algorithm in deep learning, adaptive methods like Clipped SGD/Adam have been observed to outperform SGD across important tasks, such as attention models. The settings under which SGD performs poorly in comparison to adaptive methods are n…
In extreme classification settings, embedding-based neural network models are currently not competitive with sparse linear and tree-based methods in terms of accuracy. Most prior works attribute this poor performance to the low-dimensional bottleneck in embedding-based methods. In this paper, we dem…
Adaptive methods such as Adam and RMSProp are widely used in deep learning but are not well understood. In this paper, we seek a crisp, clean and precise characterization of their behavior in nonconvex settings. To this end, we first provide a novel view of adaptive methods as preconditioned SGD, wh…
Linear encoding of sparse vectors is widely popular, but is commonly data-independent – missing any possible extra (but a priori unknown) structure beyond sparsity. In this paper we present a new method to learn linear encoders that adapt to data, while still performing well with the widely used $\e…
Neural language models have been widely used in various NLP tasks, including machine translation, next word prediction and conversational agents. However, it is challenging to deploy these models on mobile devices due to their slow prediction speed, where the bottleneck is to compute top candidates…
Multilabel classification is a challenging problem arising in applications ranging from information retrieval to image tagging. A popular approach to this problem is to employ a reduction to a suitable series of binary or multiclass problems (e.g., computing a softmax based cross-entropy over the re…
We derive the optimal $(0, \delta)$-differentially private query-output independent noise-adding mechanism for single real-valued query function under a general cost-minimization framework. Under a mild technical condition, we show that the optimal noise probability distribution is a uniform distrib…
The computational cost of training with softmax cross entropy loss grows linearly with the number of classes. For the settings where a large number of classes are involved, a common method to speed up training is to sample a subset of classes and utilize an estimate of the loss gradient based on the…
We consider the problem of retrieving the most relevant labels for a given input when the size of the output space is very large. Retrieval methods are modeled as set-valued classifiers which output a small set of classes for each input, and a mistake is made if the label is not in the output set. D…
Adaptive gradient methods that rely on scaling gradients down by the square root of exponential moving averages of past squared gradients, such RMSProp, Adam, Adadelta have found wide application in optimizing the nonconvex problems that arise in deep learning. However, it has been recently demonstr…
For problems with large output spaces, evaluation of the loss function and its gradient are expensive, typically taking linear time in the size of the output space. Recently, methods have been developed to speed up learning via efficient data structures for Nearest-Neighbor Search (NNS) or Maximum I…
Several recently proposed stochastic optimization methods that have been successfully used in training deep networks such as RMSProp, Adam, Adadelta, Nadam are based on using gradient updates scaled by square roots of exponential moving averages of squared past gradients. In many applications, e.g.…
Distributed stochastic gradient descent is an important subroutine in distributed learning. A setting of particular interest is when the clients are mobile devices, where two important concerns are communication efficiency and the privacy of the clients. Several recent works have focused on reducing…
Motivated by the need for distributed learning and optimization algorithms with low communication cost, we study communication efficient algorithms for distributed mean estimation. Unlike previous works, we make no probabilistic assumptions on the data. We first show that for $d$ dimensional data wi…
In this work, we propose a new technique for \emphfast k-nearest neighbor (k-NN) classification in which the original database is represented via a small set of learned binary prototypes. The training phase simultaneously learns a hash function which maps the data points to binary codes, and a set o…
We propose a simple, yet powerful regularization technique that can be used to significantly improve both the pairwise and triplet losses in learning local feature descriptors. The idea is that in order to fully utilize the expressive power of the descriptor space, good local feature descriptors sho…
We propose a multiscale quantization approach for fast similarity search on large, high-dimensional datasets. The key insight of the approach is that quantization methods, in particular product quantization, perform poorly when there is large variance in the norms of the data points. This is a commo…
Learning-based binary hashing has become a powerful paradigm for fast search and retrieval in massive databases. However, due to the requirement of discrete outputs for the hash functions, learning such functions is known to be very challenging. In addition, the objective functions adopted by existi…
We consider the hashing mechanism for constructing binary embeddings, that involves pseudo-random projections followed by nonlinear (sign function) mappings. The pseudo-random projection is described by a matrix, where not all entries are independent random variables but instead a fixed “budget of r…
We present an intriguing discovery related to Random Fourier Features: replacing multiplication by a random Gaussian matrix with multiplication by a properly scaled random orthogonal matrix significantly decreases kernel approximation error. We call this technique Orthogonal Random Features (ORF), a…
We propose a quantization based approach for fast approximate Maximum Inner Product Search (MIPS). Each database vector is quantized in multiple subspaces via a set of codebooks, learned directly by minimizing the inner product quantization error. Then, the inner product of a query to a database vec…
We explore the redundancy of parameters in deep neural networks by replacing the conventional linear projection in fully-connected layers with the circulant projection. The circulant structure substantially reduces memory footprint and enables the use of the Fast Fourier Transform to speed up the co…
This paper describes a large scale exemplar-based acoustic modeling approach for large vocabulary continuous speech recognition. We construct an index of labeled training frames using high-level features extracted from the bottleneck layer of a deep neural network as indexing features. At recognitio…
We propose a family of structured matrices to speed up orthogonal projections for high-dimensional data commonly seen in computer vision applications. In this, a structured matrix is formed by the Kronecker product of a series of smaller orthogonal matrices. This achieves O(dlogd) computational comp…
Compact explicit feature maps provide a practical framework to scale kernel methods to large-scale learning, but deriving such maps for many types of kernels remains a challenging open problem. Among the commonly used kernels for nonlinear classification are polynomial kernels, for which low approxi…
We consider the task of building compact deep learning pipelines suitable for deploymenton storage and power constrained mobile devices. We propose a uni-fied framework to learn a broad family of structured parameter matrices that arecharacterized by the notion of low displacement rank. Our structur…