32 accepted papers
Data filtering plays a central role in improving model performance, particularly for vision language models that are pretrained on large, noisy, and redundant image-caption datasets. Existing filtering techniques assess every sample individually and retain those that exceed a certain quality thresho…
Retrieval augmentation, the practice of retrieving additional data from large auxiliary pools, has emerged as an effective technique for enhancing model performance in the low-data regime. Prior approaches have employed only nearest-neighbor based strategies for data selection, which retrieve auxili…
The emerging capabilities of large language models (LLMs) have sparked concerns about their immediate potential for harmful misuse. The core approach to mitigate these concerns is the detection of harmful queries to the model. Current detection approaches are fallible, and are particularly susceptib
Optimizing the performance of many objectives (instantiated by tasks or clients) jointly with a few Pareto stationary solutions (models) is critical in machine learning. However, previous multi-objective optimization methods often focus on a few objectives and cannot scale to many objectives that ou…
Sharpness-Aware Minimization (SAM) has been demonstrated to improve the generalization performance of overparameterized models by seeking flat minima on the loss landscape through optimizing model parameters that incur the largest loss within a neighborhood. Nevertheless, such min-max formulations a…
Supervised finetuning (SFT) on instruction datasets has played a crucial role in achieving the remarkable zero-shot generalization capabilities observed in modern large language models (LLMs). However, the annotation efforts required to produce high quality responses for instructions are becoming pr…
Submodular functions, crucial for various applications, often lack practical learning methods for their acquisition. Seemingly unrelated, learning a scaling from oracles offering graded pairwise preferences (GPC) is underexplored, despite a rich history in psychometrics. In this paper, we introduce…
In the context of online interactive machine learning with combinatorial objectives, we extend purely submodular prior work to more general non-submodular objectives. This includes: (1) those that are additively decomposable into a sum of two terms (a monotone submodular and monotone supermodular t…
This paper explores a machine learning approach on data from a single-chip mmWave radar for generating high resolution point clouds – a key sensing primitive for robotic applications such as mapping, odometry and localization. Unlike lidar and vision-based systems, mmWave radar can operate in harsh…
In every communication round of federated learning, a random subset of clients communicate their model updates back to the server which then aggregates them all. The optimal size of this subset is not known and several studies have shown that typically random selection does not perform ve…
With ever-increasing dataset sizes, subset selection techniques are becoming increasingly important for a plethora of tasks. It is often necessary to guide the subset selection to achieve certain desiderata, which includes focusing or targeting certain data points, while avoiding others. Examples of…
Continual learning is an emerging research challenge in machine learning that addresses the problem where models quickly fit the most recently trained-on data but suffer from catastrophic forgetting of previous data due to distribution shifts --- it does this by maintaining a small historical replay…
In the robust submodular partitioning problem, we aim to allocate a set of items into $m$ blocks, so that the evaluation of the minimum block according to a submodular function is maximized. Robust submodular partitioning promotes the diversity of every block in the partition. It has many applicatio…
We study a novel curriculum learning scheme where in each round, samples are selected to achieve the greatest progress and fastest learning speed towards the ground-truth on all available samples. Inspired by an analysis of optimization dynamics under gradient flow for both regression and classifica…
Neural network training can easily overfit noisy labels resulting in poor generalization performance. Existing methods address this problem by (1) filtering out the noisy data and only using the clean data for training or (2) relabeling the noisy data by the model during training or by another model…
As an extension to the matroid span problem, we propose the submodular span problem that involves finding a large set of elements with small gain relative to a given query set. We then propose a two-stage Submodular Span Summarization (S3) framework to achieve a form of conditional or query-focused…
Incremental gradient (IG) methods, such as stochastic gradient descent and its variants are commonly used for large scale optimization in machine learning. Despite the sustained effort to make IG methods more data-efficient, it remains an open question how to select a training data subset that can t…
Semi-supervised learning (SSL) leverages unlabeled data when training a model with insufficient labeled data. A common strategy for SSL is to enforce the consistency of model outputs between similar samples, e.g., neighbors or data augmentations of the same sample. However, model outputs can vary dr…
The gradient of a deep neural network (DNN) w.r.t. the input provides information that can be used to explain the output prediction in terms of the input features and has been widely studied to assist in interpreting DNNs. In a linear model (i.e., g(x) = wx + b), the gradient corresponds to the weig…
We introduce a novel method to combat label noise when training deep neural networks for classification. We propose a loss function that permits abstention during training thereby allowing the DNN to abstain on confusing samples while continuing to learn and improve classification performance on the…
We propose a general and efficient hierarchical robust partitioning framework to generate a deterministic sequence of mini-batches, one that offers assurances of being high quality, unlike a randomly drawn sequence. We compare our deterministically generated mini-batch sequences to randomly generat…
We discuss three novel insights about dropout for DNNs with ReLUs: 1) dropout encourages each local linear piece of a DNN to be trained on data points from nearby regions; 2) the same dropout rate results in different (effective) deactivation rates for layers with different portions of ReLU-deactiva…
We introduce the problem of grouping a finite ground set into blocks where each block is a subset of the ground set and where: (i) the blocks are individually highly valued by a submodular function (both robustly and in the average case) while satisfying block-specific matroid constraints; and (ii)…
We analyze the performance of the greedy algorithm, and also a discrete semi-gradient based algorithm, for maximizing the sum of a suBmodular and suPermodular (BP) function (both of which are non-negative monotone non-decreasing) under two types of constraints, either a cardinality constraint or $p\…
We introduce and study minimax curriculum learning (MCL), a new method for adaptively selecting a sequence of training subsets for a succession of stages in machine learning. The subsets are encouraged to be small and diverse early on, and then larger, harder, and allowably more homogeneous in later…
We propose a new random pruning method (called “submodular sparsification (SS)”) to reduce the cost of submodular maximization. The pruning is applied via a “submodularity graph” over the $n$ ground elements, where each directed edge is associated with a pairwise dependency defined by the submodular…
Deep models have achieved great success on a variety of challenging tasks. How- ever, the models that achieve great performance often have an enormous number of parameters, leading to correspondingly great demands on both computational and memory resources, especially for fully-connected layers. In…
We investigate a new optimization problem involving minimizing the Ratio of Submodular (RS) functions. We argue that this problem occurs naturally in several real world applications. We then show the connection between this problem and several related problems, including minimizing the difference of…
Deep neural networks have achieved great successes on various machine learning tasks, however, there are many open fundamental questions to be answered. In this paper, we tackle the problem of quantifying the quality of learned wights of different networks with possibly different architectures, goin…
Graph smoothness objectives have achieved great success in semi-supervised learning but have not yet been applied extensively to unsupervised generative models. We define a new class of entropic graph-based posterior regularizers that augment a probabilistic model by encouraging pairs of nearby vari…
We consider learning representations (features) in the setting in which we have access to multiple unlabeled views of the data for representation learning while only one view is available at test time. Previous work on this problem has proposed several techniques based on deep neural networks, typic…
We study the problem of selecting a subset of big data to train a classifier while incurring minimal performance loss. We show the connection of submodularity to the data likelihood functions for Naive Bayes (NB) and Nearest Neighbor (NN) classifiers, and formulate the data subset selection problems…