AIConfPaper
← Search

Manzil Zaheer

68 accepted papers

2026

CIMemories: A Compositional Benchmark For Contextual Integrity In LLMs

Niloofar Mireshghallah, Neal Mangaokar, Narine Kokhlikyan, Arman Zharmagambetov, Manzil Zaheer, Saeed Mahloujifar +1
ICLR 2026poster

Large Language Models (LLMs) increasingly use persistent memory from past interactions to enhance personalization and task performance. However, this memory creates critical risks when sensitive information is revealed in inappropriate contexts. We present CIMemories, a benchmark for evaluating whet…

Cited by 0Source ↗code ↗Scholar ↗
2026

Cite Pretrain: Retrieval-Free Knowledge Attribution for Large Language Models

Yukun Huang, Sanxing Chen, Jian Pei, Manzil Zaheer, Bhuwan Dhingra
ICLR 2026poster

Trustworthy language models should provide both correct and verifiable answers. However, citations generated directly by standalone LLMs are often unreliable due to hallucinations. As a result, current systems insert citations by querying an external retriever at inference time, introducing latency,…

Cited by 0Source ↗Scholar ↗
2026

Rethinking Thinking Tokens: LLMs as Improvement Operators

Lovish Madaan, Aniket Didolkar, Suchin Gururangan, John Quan, Ruan Silva, Russ Salakhutdinov +3
ICML 2026poster

Reasoning training incentivizes LLMs to produce long chains of thought (long CoT), which among other things, allows them to explore solution strategies with self-checking. This results in higher accuracy, but inflates context length, token/compute cost, and answer latency. We ask: Can current models…

Cited by 0Source ↗Scholar ↗
2026

The Art of Scaling Reinforcement Learning Compute for LLMs

Fnu Devvrit, Lovish Madaan, Rishabh Tiwari, Rachit Bansal, Sai Surya Duvvuri, Manzil Zaheer +3
ICLR 2026oral

Reinforcement learning (RL) has become central to training large language models (LLMs), yet the field lacks predictive scaling methodologies comparable to those established for pre-training. Despite rapidly rising compute budgets, there is no principled understanding of how to evaluate algo…

Cited by 0Source ↗Scholar ↗
2025

Understanding outer learning rates in Local SGD

Ahmed Khaled, Satyen Kale, Arthur Douillard, Chi Jin, Rob Fergus, Manzil Zaheer
NeurIPS 2025poster

Modern machine learning often requires training with large batch size, distributed data, and massively parallel compute hardware (like mobile and other edge devices or distributed data centers). Communication becomes a major bottleneck in such settings but methods like Local Stochastic Gradient Desc…

Cited by 0Source ↗Scholar ↗
2024

A Fresh Take on Stale Embeddings: Improving Dense Retriever Training with Corrector Networks

Nicholas Monath, Will Sussman Grathwohl, Michael Boratko, Rob Fergus, Andrew McCallum, Manzil Zaheer
ICML 2024poster

In dense retrieval, deep encoders provide embeddings for both inputs and targets, and the softmax function is used to parameterize a distribution over a large number of candidate targets (e.g., textual passages for information retrieval). Significant challenges arise in training such encoders in the…

Cited by 0Source ↗PDF ↗Scholar ↗
2024

A Statistical Framework for Data-dependent Retrieval-Augmented Models

Soumya Basu, Ankit Singh Rawat, Manzil Zaheer
ICML 2024poster

Modern ML systems increasingly augment input instances with additional relevant information to enhance final prediction. Despite growing interest in such retrieval-augmented models, their fundamental properties and training are not well understood. We propose a statistical framework to study such mo…

Cited by 0Source ↗PDF ↗Scholar ↗
2024

Adaptive Retrieval and Scalable Indexing for k-NN Search with Cross-Encoders

Nishant Yadav, Nicholas Monath, Manzil Zaheer, Rob Fergus, Andrew McCallum
ICLR 2024poster

Cross-encoder (CE) models which compute similarity by jointly encoding a query-item pair perform better than using dot-product with embedding-based models (dual-encoders) at estimating query-item relevance. Existing approaches perform k-NN search with cross-encoders by approximating the CE similarit…

Cited by 0Source ↗PDF ↗Scholar ↗
2024

Analysis of Plan-based Retrieval for Grounded Text Generation

Ameya Godbole, Nicholas Monath, Seungyeon Kim, Ankit Singh Rawat, Andrew McCallum, Manzil Zaheer
EMNLP 2024main

In text generation, hallucinations refer to the generation of seemingly coherent text that contradicts established knowledge. One compelling hypothesis is that hallucinations occur when a language model is given a generation task outside its parametric knowledge (due to rarity, recency, domain, etc.…

Cited by 1Source ↗PDF ↗Scholar ↗
2024

Can Public Large Language Models Help Private Cross-device Federated Learning?

Boxin Wang, Yibo Zhang, Yuan Cao, Bo Li, Hugh McMahan, Sewoong Oh +2
NAACL 2024findings

We study (differentially) private federated learning (FL) of language models. The language models in cross-device FL are relatively small, which can be trained with meaningful formal user-level differential privacy (DP) guarantees when massive parallelism in training is enabled by the participation…

Cited by 45Source ↗PDF ↗Scholar ↗
2024

ExeDec: Execution Decomposition for Compositional Generalization in Neural Program Synthesis

Kensen Shi, Joey Hong, Yinlin Deng, Pengcheng Yin, Manzil Zaheer, Charles Sutton
ICLR 2024oral

When writing programs, people have the ability to tackle a new complex task by decomposing it into smaller and more familiar subtasks. While it is difficult to measure whether neural program synthesis methods have similar capabilities, we can measure whether they compositionally generalize, that is,…

Cited by 19Source ↗PDF ↗Scholar ↗
2024

Functional Interpolation for Relative Positions improves Long Context Transformers

Shanda Li, Chong You, Guru Guruganesh, Joshua Ainslie, Santiago Ontanon, Manzil Zaheer +4
ICLR 2024poster

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…

Cited by 47Source ↗PDF ↗Scholar ↗
2024

USTAD: Unified Single-model Training Achieving Diverse Scores for Information Retrieval

Seungyeon Kim, Ankit Singh Rawat, Manzil Zaheer, Wittawat Jitkrittum, Veeranjaneyulu Sadhanala, Sadeep Jayasumana +3
ICML 2024poster

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…

Cited by 0Source ↗PDF ↗Scholar ↗
2023

Differentially Private Adaptive Optimization with Delayed Preconditioners

Tian Li, Manzil Zaheer, Ken Liu, Sashank J. Reddi, Hugh Brendan McMahan, Virginia Smith
ICLR 2023poster

Privacy costs may negate the benefits of using adaptive optimizers in differentially private model training. Prior works typically address this issue by using auxiliary information (e.g., public data) to boost the effectiveness of adaptive optimization. In this work, we explore techniques to estimat…

Cited by 13Source ↗PDF ↗code ↗Scholar ↗
2023

Efficient k-NN Search with Cross-Encoders using Adaptive Multi-Round CUR Decomposition

Nishant Yadav, Nicholas Monath, Manzil Zaheer, Andrew McCallum
EMNLP 2023short findings

Cross-encoder models, which jointly encode and score a query-item pair, are prohibitively expensive for direct k-nearest neighbor (k-NN) search. Consequently, k-NN search typically employs a fast approximate retrieval (e.g. using BM25 or dual-encoder vectors), followed by reranking with a cross-enco…

Cited by 0Source ↗code ↗Scholar ↗
2023

Improving Dual-Encoder Training through Dynamic Indexes for Negative Mining

Nicholas Monath, Manzil Zaheer, Kelsey Allen, Andrew Mccallum
AISTATS 2023poster

Dual encoder models are ubiquitous in modern classification and retrieval. Crucial for training such dual encoders is an accurate estimation of gradients from the partition function of the softmax over the large output space; this requires finding negative targets that contribute most significantly…

Cited by 6Source ↗PDF ↗Scholar ↗
2023

Large Language Models with Controllable Working Memory

Daliang Li, Ankit Singh Rawat, Manzil Zaheer, Xin Wang, Michal Lukasik, Andreas Veit +2
ACL 2023findings

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…

Cited by 148Source ↗PDF ↗Scholar ↗
2023

Machine Reading Comprehension using Case-based Reasoning

Dung Ngoc Thai, Dhruv Agarwal, Mudit Chaudhary, Wenlong Zhao, Rajarshi Das, Jay-Yoon Lee +3
EMNLP 2023long findings

We present an accurate and interpretable method for answer extraction in machine reading comprehension that is reminiscent of case-based reasoning (CBR) from classical AI. Our method (CBR-MRC) builds upon the hypothesis that contextualized answers to similar questions share semantic similarities wit…

Cited by 0Source ↗Scholar ↗
2023

Multi-Task Off-Policy Learning from Bandit Feedback

Joey Hong, Branislav Kveton, Manzil Zaheer, Sumeet Katariya, Mohammad Ghavamzadeh
ICML 2023poster

Many practical problems involve solving similar tasks. In recommender systems, the tasks can be users with similar preferences; in search engines, the tasks can be items with similar affinities. To learn statistically efficiently, the tasks can be organized in a hierarchy, where the task affinity is…

Cited by 10Source ↗PDF ↗Scholar ↗
2023

ResMem: Learn what you can and memorize the rest

Zitong Yang, Michal Lukasik, Vaishnavh Nagarajan, Zonglin Li, Ankit Singh Rawat, Manzil Zaheer +2
NeurIPS 2023poster

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…

Cited by 12Source ↗PDF ↗Scholar ↗
2023

Teacher Guided Training: An Efficient Framework for Knowledge Transfer

Manzil Zaheer, Ankit Singh Rawat, Seungyeon Kim, Chong You, Himanshu Jain, Andreas Veit +2
ICLR 2023poster

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)…

Cited by 2Source ↗PDF ↗Scholar ↗
2022

A Context-Integrated Transformer-Based Neural Network for Auction Design

Zhijian Duan, Jingwu Tang, Yutong Yin, Zhe Feng, Xiang Yan, Manzil Zaheer +1
ICML 2022spotlight

One of the central problems in auction design is developing an incentive-compatible mechanism that maximizes the auctioneer’s expected revenue. While theoretical approaches have encountered bottlenecks in multi-item auctions, recently, there has been much progress on finding the optimal mechanism th…

Cited by 40Source ↗PDF ↗code ↗Scholar ↗
2022

A Fourier Approach to Mixture Learning

Mingda Qiao, Guru Guruganesh, Ankit Singh Rawat, Kumar Avinava Dubey, Manzil Zaheer
NeurIPS 2022accept

We revisit the problem of learning mixtures of spherical Gaussians. Given samples from a mixture $\frac{1}{k}\sum_{j=1}^{k}\mathcal{N}(\mu_j, I_d)$, the goal is to estimate the means $\mu_1, \mu_2, \ldots, \mu_k \in \mathbb{R}^d$ up to a small error. The hardness of this learning problem can be meas…

Cited by 9Source ↗PDF ↗Scholar ↗
2022

Efficient Nearest Neighbor Search for Cross-Encoder Models using Matrix Factorization

Nishant Yadav, Nicholas Monath, Rico Angell, Manzil Zaheer, Andrew McCallum
EMNLP 2022main

Efficient k-nearest neighbor search is a fundamental task, foundational for many problems in NLP. When the similarity is measured by dot-product between dual-encoder vectors or L2-distance, there already exist many scalable and efficient search methods. But not so when similarity is measured by more…

Cited by 14Source ↗PDF ↗code ↗Scholar ↗
2022

Knowledge Base Question Answering by Case-based Reasoning over Subgraphs

Rajarshi Das, Ameya Godbole, Ankita Naik, Elliot Tower, Manzil Zaheer, Hannaneh Hajishirzi +2
ICML 2022spotlight

Question answering (QA) over knowledge bases (KBs) is challenging because of the diverse, essentially unbounded, types of reasoning patterns needed. However, we hypothesize in a large KB, reasoning patterns required to answer a query type reoccur for various entities in their respective subgraph nei…

Cited by 79Source ↗PDF ↗code ↗Scholar ↗
2022

Learning to Navigate Wikipedia by Taking Random Walks

Manzil Zaheer, Kenneth Marino, Will Sussman Grathwohl, John Schultz, Wendy Shang, Sheila Babayan +4
NeurIPS 2022accept

A fundamental ability of an intelligent web-based agent is seeking out and acquiring new information. Internet search engines reliably find the correct vicinity but the top results may be a few links away from the desired target. A complementary approach is navigation via hyperlinks, employing a pol…

Cited by 5Source ↗PDF ↗Scholar ↗
2022

Private Adaptive Optimization with Side information

Tian Li, Manzil Zaheer, Sashank Reddi, Virginia Smith
ICML 2022spotlight

Adaptive optimization methods have become the default solvers for many machine learning tasks. Unfortunately, the benefits of adaptivity may degrade when training with differential privacy, as the noise added to ensure privacy reduces the effectiveness of the adaptive preconditioner. To this end, we…

Cited by 38Source ↗PDF ↗code ↗Scholar ↗
2022

Robust Training of Neural Networks Using Scale Invariant Architectures

Zhiyuan Li, Srinadh Bhojanapalli, Manzil Zaheer, Sashank Reddi, Sanjiv Kumar
ICML 2022oral

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…

Cited by 34Source ↗PDF ↗Scholar ↗
2022

StreamingQA: A Benchmark for Adaptation to New Knowledge over Time in Question Answering Models

Adam Liska, Tomas Kocisky, Elena Gribovskaya, Tayfun Terzi, Eren Sezener, Devang Agrawal +8
ICML 2022spotlight

Knowledge and language understanding of models evaluated through question answering (QA) has been usually studied on static snapshots of knowledge, like Wikipedia. However, our world is dynamic, evolves over time, and our models’ knowledge becomes outdated. To study how semi-parametric QA models and…

Cited by 62Source ↗PDF ↗code ↗Scholar ↗
2022

Thompson Sampling with a Mixture Prior

Joey Hong, Branislav Kveton, Manzil Zaheer, Mohammad Ghavamzadeh, Craig Boutilier
AISTATS 2022poster

We study Thompson sampling (TS) in online decision making, where the uncertain environment is sampled from a mixture distribution. This is relevant in multi-task learning, where a learning agent faces different classes of problems. We incorporate this structure in a natural way by initializing TS wi…

Cited by 18Source ↗PDF ↗Scholar ↗
2021

Adaptive Federated Optimization

Sashank J. Reddi, Zachary Charles, Manzil Zaheer, Zachary Garrett, Keith Rush, Jakub Konečný +2
ICLR 2021poster

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…

Cited by 1819Source ↗PDF ↗code ↗Scholar ↗
2021

Anchor & Transform: Learning Sparse Embeddings for Large Vocabularies

Paul Pu Liang, Manzil Zaheer, Yuan Wang, Amr Ahmed
ICLR 2021poster

Learning continuous representations of discrete objects such as text, users, movies, and URLs lies at the heart of many applications including language and user modeling. When using discrete objects as input to neural networks, we often ignore the underlying structures (e.g., natural groupings and s…

Cited by 13Source ↗PDF ↗Scholar ↗
2021

Case-based Reasoning for Natural Language Queries over Knowledge Bases

Rajarshi Das, Manzil Zaheer, Dung Thai, Ameya Godbole, Ethan Perez, Jay Yoon Lee +3
EMNLP 2021main

It is often challenging to solve a complex problem from scratch, but much easier if we can access other similar problems with their solutions — a paradigm known as case-based reasoning (CBR). We propose a neuro-symbolic CBR approach (CBR-KBQA) for question answering over large knowledge bases. CBR-K…

Cited by 81Source ↗PDF ↗Scholar ↗
2021

DAG-Structured Clustering by Nearest Neighbors

Nicholas Monath, Manzil Zaheer, Kumar Avinava Dubey, Amr Ahmed, Andrew McCallum
AISTATS 2021poster

Hierarchical clusterings compactly encode multiple granularities of clusters within a tree structure. Hierarchies, by definition, fail to capture different flat partitions that are not subsumed in one another. In this paper, we advocate for an alternative structure for representing multiple clusteri…

Cited by 3Source ↗PDF ↗Scholar ↗
2021

Differentiable Open-Ended Commonsense Reasoning

Bill Yuchen Lin, Haitian Sun, Bhuwan Dhingra, Manzil Zaheer, Xiang Ren, William Cohen
NAACL 2021long

Current commonsense reasoning research focuses on developing models that use commonsense knowledge to answer multiple-choice questions. However, systems designed to answer multiple-choice questions may not be useful in applications that do not provide a small list of candidate answers to choose from…

Cited by 44Source ↗PDF ↗Scholar ↗
2021

Exact and approximate hierarchical clustering using A*

Craig S. Greenberg, Sebastian Macaluso, Nicholas Monath, Avinava Dubey, Patrick Flaherty, Manzil Zaheer +3
UAI 2021poster

Hierarchical clustering is a critical task in numerous domains. Many approaches are based on heuristics and the properties of the resulting clusterings are studied post hoc. However, in several applications, there is a natural cost function that can be used to characterize the quality of the cluster…

Cited by 5Source ↗PDF ↗Scholar ↗
2021

Latent Programmer: Discrete Latent Codes for Program Synthesis

Joey Hong, David Dohan, Rishabh Singh, Charles Sutton, Manzil Zaheer
ICML 2021oral

A key problem in program synthesis is searching over the large space of possible programs. Human programmers might decide the high-level structure of the desired program before thinking about the details; motivated by this intuition, we consider two-level search for program synthesis, in which the s…

Cited by 26Source ↗PDF ↗Scholar ↗
2021

Meta-Thompson Sampling

Branislav Kveton, Mikhail Konobeev, Manzil Zaheer, Chih-Wei Hsu, Martin Mladenov, Craig Boutilier +1
ICML 2021spotlight

Efficient exploration in bandits is a fundamental online learning problem. We propose a variant of Thompson sampling that learns to explore better as it interacts with bandit instances drawn from an unknown prior. The algorithm meta-learns the prior and thus we call it MetaTS. We propose several eff…

Cited by 84Source ↗PDF ↗Scholar ↗
2021

Unsupervised Abstractive Dialogue Summarization for Tete-a-Tetes

Xinyuan Zhang, Ruiyi Zhang, Manzil Zaheer, Amr Ahmed
AAAI 2021technical

High-quality dialogue-summary paired data is expensive to produce and domain-sensitive, making abstractive dialogue summarization a challenging task. In this work, we propose the first unsupervised abstractive dialogue summarization model for tete-a-tetes (SuTaT). Unlike standard text summarization,…

Cited by 34Source ↗PDF ↗Scholar ↗
2020

Big Bird: Transformers for Longer Sequences

Manzil Zaheer, Guru Guruganesh, Kumar Avinava Dubey, Joshua Ainslie, Chris Alberti, Santiago Ontanon +5
NeurIPS 2020poster

Transformers-based models, such as BERT, have been one of the most successful deep learning models for NLP. Unfortunately, one of their core limitations is the quadratic dependency (mainly in terms of memory) on the sequence length due to their full attention mechanism. To remedy this, we propose,…

Cited by 2778Source ↗PDF ↗code ↗Scholar ↗
2020

Differentiable Meta-Learning of Bandit Policies

Craig Boutilier, Chih-wei Hsu, Branislav Kveton, Martin Mladenov, Csaba Szepesvari, Manzil Zaheer
NeurIPS 2020poster

Exploration policies in Bayesian bandits maximize the average reward over problem instances drawn from some distribution P. In this work, we learn such policies for an unknown distribution P using samples from P. Our approach is a form of meta-learning and exploits properties of P without making str…

Cited by 30Source ↗PDF ↗code ↗Scholar ↗
2020

Differentiable Reasoning over a Virtual Knowledge Base

Bhuwan Dhingra, Manzil Zaheer, Vidhisha Balachandran, Graham Neubig, Ruslan Salakhutdinov, William W. Cohen
ICLR 2020talk

We consider the task of answering complex multi-hop questions using a corpus as a virtual knowledge base (KB). In particular, we describe a neural module, DrKIT, that traverses textual data like a KB, softly following paths of relations between mentions of entities in the corpus. At each step the mo…

Cited by 103Source ↗Scholar ↗
2020

PLLay: Efficient Topological Layer based on Persistent Landscapes

Kwangho Kim, Jisu Kim, Manzil Zaheer, Joon Kim, Frederic Chazal, Larry Wasserman
NeurIPS 2020poster

We propose PLLay, a novel topological layer for general deep learning models based on persistence landscapes, in which we can efficiently exploit the underlying topological features of the input data structure. In this work, we show differentiability with respect to layer inputs, for a general persi…

Cited by 77Source ↗PDF ↗code ↗Scholar ↗
2020

Randomized Exploration in Generalized Linear Bandits

Branislav Kveton, Manzil Zaheer, Csaba Szepesvari, Lihong Li, Mohammad Ghavamzadeh, Craig Boutilier
AISTATS 2020poster

We study two randomized algorithms for generalized linear bandits. The first, GLM-TSL, samples a generalized linear model (GLM) from the Laplace approximation to the posterior distribution. The second, GLM-FPL, fits a GLM to a randomly perturbed history of past rewards. We analyze both algorithms an…

Cited by 138Source ↗PDF ↗Scholar ↗
2020

Robust large-margin learning in hyperbolic space

Melanie Weber, Manzil Zaheer, Ankit Singh Rawat, Aditya K Menon, Sanjiv Kumar
NeurIPS 2020poster

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…

Cited by 40Source ↗PDF ↗Scholar ↗
2019

Multi-step Retriever-Reader Interaction for Scalable Open-domain Question Answering

Rajarshi Das, Shehzaad Dhuliawala, Manzil Zaheer, Andrew McCallum
ICLR 2019poster

This paper introduces a new framework for open-domain question answering in which the retriever and the reader \emph{iteratively interact} with each other. The framework is agnostic to the architecture of the machine reading model provided it has \emph{access} to the token-level hidden representatio…

Cited by 225Source ↗PDF ↗code ↗Scholar ↗
2019

Towards Gradient Free and Projection Free Stochastic Optimization

Anit Kumar Sahu, Manzil Zaheer, Soummya Kar
AISTATS 2019poster

This paper focuses on the problem of \emph{constrained} \emph{stochastic} optimization. A zeroth order Frank-Wolfe algorithm is proposed, which in addition to the projection-free nature of the vanilla Frank-Wolfe algorithm makes it gradient free. Under convexity and smoothness assumption, we show th…

Cited by 48Source ↗PDF ↗Scholar ↗
2018

A Generic Approach for Escaping Saddle points

Sashank Reddi, Manzil Zaheer, Suvrit Sra, Barnabas Poczos, Francis Bach, Ruslan Salakhutdinov +1
AISTATS 2018poster

A central challenge to using first-order methods for optimizing nonconvex problems is the presence of saddle points. First-order methods often get stuck at saddle points, greatly deteriorating their performance. Typically, to escape from saddles one has to use second-order methods. However, most wor…

Cited by 0Source ↗PDF ↗Scholar ↗
2018

Adaptive Methods for Nonconvex Optimization

Manzil Zaheer, Sashank Reddi, Devendra Sachan, Satyen Kale, Sanjiv Kumar
NeurIPS 2018poster

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…

Cited by 523Source ↗PDF ↗code ↗Scholar ↗
2018

Compressed Video Action Recognition

Chao-Yuan Wu, Manzil Zaheer, Hexiang Hu, R. Manmatha, Alexander J. Smola, Philipp Krähenbühl
CVPR 2018poster

Training robust deep video representations has proven to be much more challenging than learning deep image representations. This is in part due to the enormous size of raw video streams and the high temporal redundancy; the true and interesting signal is often drowned in too much irrelevant data. Mo…

Cited by 428Source ↗PDF ↗Scholar ↗
2018

Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning

Rajarshi Das, Shehzaad Dhuliawala, Manzil Zaheer, Luke Vilnis, Ishan Durugkar, Akshay Krishnamurthy +2
ICLR 2018poster

Knowledge bases (KB), both automatically and manually constructed, are often incomplete --- many valid facts can be inferred from the KB by synthesizing existing information. A popular approach to KB completion is to infer new relations by combinatory reasoning over the information found along other…

Cited by 701Source ↗PDF ↗code ↗Scholar ↗
2018

Nonparametric Density Estimation under Adversarial Losses

Shashank Singh, Ananya Uppal, Boyue Li, Chun-Liang Li, Manzil Zaheer, Barnabas Poczos
NeurIPS 2018poster

We study minimax convergence rates of nonparametric density estimation under a large class of loss functions called ``adversarial losses'', which, besides classical L^p losses, includes maximum mean discrepancy (MMD), Wasserstein distance, and total variation distance. These losses are closely relat…

Cited by 94Source ↗PDF ↗Scholar ↗
2018

Transformation Autoregressive Networks

Junier Oliva, Avinava Dubey, Manzil Zaheer, Barnabas Poczos, Ruslan Salakhutdinov, Eric Xing +1
ICML 2018oral

The fundamental task of general density estimation $p(x)$ has been of keen interest to machine learning. In this work, we attempt to systematically characterize methods for density estimation. Broadly speaking, most of the existing methods can be categorized into either using:

Cited by 100Source ↗PDF ↗code ↗Scholar ↗
2017

Deep Sets

Manzil Zaheer, Satwik Kottur, Siamak Ravanbakhsh, Barnabas Poczos, Ruslan Salakhutdinov, Alexander J Smola
NeurIPS 2017oral

We study the problem of designing models for machine learning tasks defined on sets. In contrast to the traditional approach of operating on fixed dimensional vectors, we consider objective functions defined on sets and are invariant to permutations. Such problems are widespread, ranging from the es…

Cited by 3299Source ↗PDF ↗code ↗Scholar ↗
2017

Latent LSTM Allocation: Joint Clustering and Non-Linear Dynamic Modeling of Sequence Data

Manzil Zaheer, Amr Ahmed, Alexander J. Smola
ICML 2017poster

Recurrent neural networks, such as long-short term memory (LSTM) networks, are powerful tools for modeling sequential data like user browsing history (Tan et al., 2016; Korpusik et al., 2016) or natural language text (Mikolov et al., 2010). However, to generalize across different user types, LSTMs r…

Cited by 78Source ↗PDF ↗Scholar ↗
2016

Exponential Stochastic Cellular Automata for Massively Parallel Inference

Manzil Zaheer, Michael Wick, Jean-Baptiste Tristan, Alex Smola, Guy Steele
AISTATS 2016poster

We propose an embarrassingly parallel, memory efficient inference algorithm for latent variable models in which the complete data likelihood is in the exponential family. The algorithm is a stochastic cellular automaton and converges to a valid maximum a posteriori fixed point. Applied to latent Dir…

Cited by 30Source ↗PDF ↗Scholar ↗