| 2025 | ICLR | Instruct-SkillMix: A Powerful Pipeline for LLM Instruction Tuning. | Simran Kaur, Simon Park, Anirudh Goyal, Sanjeev Arora |
| 2025 | ICLR | Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization. | Noam Razin, Sadhika Malladi, Adithya Bhaskar, Danqi Chen, Sanjeev Arora, Boris Hanin |
| 2025 | ICLR | Provable unlearning in topic modeling and downstream tasks. | Stanley Wei, Sadhika Malladi, Sanjeev Arora, Amartya Sanyal |
| 2025 | ICML | Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs? | Simon Park, Abhishek Panigrahi, Yun Cheng, Dingli Yu, Anirudh Goyal, Sanjeev Arora |
| 2025 | ICML | Weak-to-Strong Generalization Even in Random Feature Networks, Provably. | Marko Medvedev, Kaifeng Lyu, Dingli Yu, Sanjeev Arora, Zhiyuan Li, Nathan Srebro |
| 2025 | ICML | On the Power of Context-Enhanced Learning in LLMs. | Xingyu Zhu, Abhishek Panigrahi, Sanjeev Arora |
| 2024 | ICLR | A Quadratic Synchronization Rule for Distributed Deep Learning. | Xinran Gu, Kaifeng Lyu, Sanjeev Arora, Jingzhao Zhang, Longbo Huang |
| 2024 | ICLR | SKILL-MIX: a Flexible and Expandable Family of Evaluations for AI Models. | Dingli Yu, Simran Kaur, Arushi Gupta, Jonah Brown-Cohen, Anirudh Goyal, Sanjeev Arora |
| 2024 | ICML | Language Models as Science Tutors. | Alexis Chevalier, Jiayi Geng, Alexander Wettig, Howard Chen, Sebastian Mizera, Toni Annala, Max Jameson Aragon, Arturo Rodrguez Fanlo, Simon Frieder, Simon Machado, Akshara Prabhakar, Ellie Thieu, Jiachen T. Wang, Zirui Wang, Xindi Wu, Mengzhou Xia, Wenhan Xia, Jiatong Yu, Junjie Zhu, Zhiyong Jason Ren, Sanjeev Arora, Danqi Chen |
| 2024 | ICML | Trainable Transformer in Transformer. | Abhishek Panigrahi, Sadhika Malladi, Mengzhou Xia, Sanjeev Arora |
| 2024 | ICML | LESS: Selecting Influential Data for Targeted Instruction Tuning. | Mengzhou Xia, Sadhika Malladi, Suchin Gururangan, Sanjeev Arora, Danqi Chen |
| 2024 | KDD | From Word-prediction to Complex Skills: Compositional Thinking and Metacognition in LLMs. | Sanjeev Arora |
| 2023 | EMNLP | Do Transformers Parse while Predicting the Masked Word? | Haoyu Zhao, Abhishek Panigrahi, Rong Ge, Sanjeev Arora |
| 2023 | ICLR | Why (and When) does Local SGD Generalize Better than SGD? | Xinran Gu, Kaifeng Lyu, Longbo Huang, Sanjeev Arora |
| 2023 | ICLR | Understanding Influence Functions and Datamodels via Harmonic Analysis. | Nikunj Saunshi, Arushi Gupta, Mark Braverman, Sanjeev Arora |
| 2023 | ICML | A Kernel-Based View of Language Model Fine-Tuning. | Sadhika Malladi, Alexander Wettig, Dingli Yu, Danqi Chen, Sanjeev Arora |
| 2023 | ICML | Task-Specific Skill Localization in Fine-tuned Language Models. | Abhishek Panigrahi, Nikunj Saunshi, Haoyu Zhao, Sanjeev Arora |
| 2022 | ICLR | What Happens after SGD Reaches Zero Loss? --A Mathematical Framework. | Zhiyuan Li, Tianhao Wang, Sanjeev Arora |
| 2022 | ICLR | On Predicting Generalization using GANs. | Yi Zhang, Arushi Gupta, Nikunj Saunshi, Sanjeev Arora |
| 2022 | ICML | Understanding Gradient Descent on the Edge of Stability in Deep Learning. | Sanjeev Arora, Zhiyuan Li, Abhishek Panigrahi |
| 2022 | ICML | Understanding Contrastive Learning Requires Incorporating Inductive Biases. | Nikunj Saunshi, Jordan T. Ash, Surbhi Goel, Dipendra Misra, Cyril Zhang, Sanjeev Arora, Sham M. Kakade, Akshay Krishnamurthy |
| 2021 | ICLR | Why Are Convolutional Nets More Sample-Efficient than Fully-Connected Nets? | Zhiyuan Li, Yi Zhang, Sanjeev Arora |
| 2021 | ICLR | A Mathematical Exploration of Why Language Models Help Solve Downstream Tasks. | Nikunj Saunshi, Sadhika Malladi, Sanjeev Arora |
| 2021 | SIGMETRICS | Opening the Black Box of Deep Learning: Some Lessons and Take-aways. | Sanjeev Arora |
| 2020 | EMNLP | TextHide: Tackling Data Privacy for Language Understanding Tasks. | Yangsibo Huang, Zhao Song, Danqi Chen, Kai Li, Sanjeev Arora |
| 2020 | ICLR | An Exponential Learning Rate Schedule for Deep Learning. | Zhiyuan Li, Sanjeev Arora |
| 2020 | ICLR | Harnessing the Power of Infinitely Wide Deep Nets on Small-data Tasks. | Sanjeev Arora, Simon S. Du, Zhiyuan Li, Ruslan Salakhutdinov, Ruosong Wang, Dingli Yu |
| 2020 | ICML | Provable Representation Learning for Imitation Learning via Bi-level Optimization. | Sanjeev Arora, Simon S. Du, Sham M. Kakade, Yuping Luo, Nikunj Saunshi |
| 2020 | ICML | InstaHide: Instance-hiding Schemes for Private Distributed Learning. | Yangsibo Huang, Zhao Song, Kai Li, Sanjeev Arora |
| 2020 | ICML | A Sample Complexity Separation between Non-Convex and Convex Meta-Learning. | Nikunj Saunshi, Yi Zhang, Mikhail Khodak, Sanjeev Arora |
| 2019 | ICLR | A Convergence Analysis of Gradient Descent for Deep Linear Neural Networks. | Sanjeev Arora, Nadav Cohen, Noah Golowich, Wei Hu |
| 2019 | ICLR | Theoretical Analysis of Auto Rate-Tuning by Batch Normalization. | Sanjeev Arora, Zhiyuan Li, Kaifeng Lyu |
| 2019 | ICML | Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks. | Sanjeev Arora, Simon S. Du, Wei Hu, Zhiyuan Li, Ruosong Wang |
| 2019 | ICML | A Theoretical Analysis of Contrastive Unsupervised Representation Learning. | Nikunj Saunshi, Orestis Plevrakis, Sanjeev Arora, Mikhail Khodak, Hrishikesh Khandeparkar |
| 2018 | ACL | A La Carte Embedding: Cheap but Effective Induction of Semantic Feature Vectors. | Mikhail Khodak, Nikunj Saunshi, Yingyu Liang, Tengyu Ma, Brandon Stewart, Sanjeev Arora |
| 2018 | COLT | An Analysis of the t-SNE Algorithm for Data Visualization. | Sanjeev Arora, Wei Hu, Pravesh K. Kothari |
| 2018 | ICLR | Towards Provable Control for Unknown Linear Dynamical Systems. | Sanjeev Arora, Elad Hazan, Holden Lee, Karan Singh, Cyril Zhang, Yi Zhang |
| 2018 | ICLR | A Compressed Sensing View of Unsupervised Text Embeddings, Bag-of-n-Grams, and LSTMs. | Sanjeev Arora, Mikhail Khodak, Nikunj Saunshi, Kiran Vodrahalli |
| 2018 | ICLR | Do GANs learn the distribution? Some Theory and Empirics. | Sanjeev Arora, Andrej Risteski, Yi Zhang |
| 2018 | ICML | Stronger Generalization Bounds for Deep Nets via a Compression Approach. | Sanjeev Arora, Rong Ge, Behnam Neyshabur, Yi Zhang |
| 2018 | ICML | On the Optimization of Deep Networks: Implicit Acceleration by Overparameterization. | Sanjeev Arora, Nadav Cohen, Elad Hazan |
| 2017 | COLT | On the Ability of Neural Nets to Express Distributions. | Holden Lee, Rong Ge, Tengyu Ma, Andrej Risteski, Sanjeev Arora |
| 2017 | ICLR | A Simple but Tough-to-Beat Baseline for Sentence Embeddings. | Sanjeev Arora, Yingyu Liang, Tengyu Ma |
| 2017 | ICML | Generalization and Equilibrium in Generative Adversarial Nets (GANs). | Sanjeev Arora, Rong Ge, Yingyu Liang, Tengyu Ma, Yi Zhang |
| 2017 | STOC | Provable learning of noisy-OR networks. | Sanjeev Arora, Rong Ge, Tengyu Ma, Andrej Risteski |
| 2016 | ICML | Provable Algorithms for Inference in Topic Models. | Sanjeev Arora, Rong Ge, Frederic Koehler, Tengyu Ma, Ankur Moitra |
| 2015 | COLT | Simple, Efficient, and Neural Algorithms for Sparse Coding. | Sanjeev Arora, Rong Ge, Tengyu Ma, Ankur Moitra |
| 2015 | STACS | Overcoming Intractability in Unsupervised Learning (Invited Talk). | Sanjeev Arora |
| 2014 | COLT | New Algorithms for Learning Incoherent and Overcomplete Dictionaries. | Sanjeev Arora, Rong Ge, Ankur Moitra |
| 2014 | ICML | Provable Bounds for Learning Some Deep Representations. | Sanjeev Arora, Aditya Bhaskara, Rong Ge, Tengyu Ma |
| 2013 | FOCS | Towards a Better Approximation for Sparsest Cut? | Sanjeev Arora, Rong Ge, Ali Kemal Sinop |
| 2013 | ICML | A Practical Algorithm for Topic Modeling with Provable Guarantees. | Sanjeev Arora, Rong Ge, Yonatan Halpern, David M. Mimno, Ankur Moitra, David A. Sontag, Yichen Wu, Michael Zhu |
| 2012 | FOCS | Learning Topic Models - Going beyond SVD. | Sanjeev Arora, Rong Ge, Ankur Moitra |
| 2012 | STOC | Computing a nonnegative matrix factorization - provably. | Sanjeev Arora, Rong Ge, Ravindran Kannan, Ankur Moitra |
| 2011 | FIE | Visualizing conductive and convective heat transfer using thermographic techniques. | Masoud Naghedolfeizi, Sanjeev Arora, James E. Glover |
| 2011 | ICALP | New Algorithms for Learning in Presence of Errors. | Sanjeev Arora, Rong Ge |
| 2011 | ISAAC | Semidefinite Programming and Approximation Algorithms: A Survey. | Sanjeev Arora |
| 2010 | FOCS | Subexponential Algorithms for Unique Games and Related Problems. | Sanjeev Arora, Boaz Barak, David Steurer |
| 2009 | ICALP | Towards a Study of Low-Complexity Graphs. | Sanjeev Arora, David Steurer, Avi Wigderson |
| 2009 | STOC | Message passing algorithms and improved LP decoding. | Sanjeev Arora, Constantinos Daskalakis, David Steurer |
| 2008 | STOC | Unique games on expanding constraint graphs are easy: extended abstract. | Sanjeev Arora, Subhash Khot, Alexandra Kolla, David Steurer, Madhur Tulsiani, Nisheeth K. Vishnoi |
| 2007 | STOC | A combinatorial, primal-dual approach to semidefinite programs. | Sanjeev Arora, Satyen Kale |
| 2006 | SODA | Local versus global properties of metric spaces. | Sanjeev Arora, Lszl Lovsz, Ilan Newman, Yuval Rabani, Yuri Rabinovich, Santosh S. Vempala |
| 2006 | STOC | New approximation guarantee for chromatic number. | Sanjeev Arora, Eden Chlamtac |
| 2005 | FOCS | On Non-Approximability for Quadratic Programs. | Sanjeev Arora, Eli Berger, Elad Hazan, Guy Kindler, Muli Safra |
| 2005 | FOCS | Fast Algorithms for Approximate Semide.nite Programming using the Multiplicative Weights Update Method. | Sanjeev Arora, Elad Hazan, Satyen Kale |
| 2005 | STOC | Towards strong nonapproximability results in the Lovasz-Schrijver hierarchy. | Michael Alekhnovich, Sanjeev Arora, Iannis Tourlakis |
| 2005 | STOC | Euclidean distortion and the sparsest cut. | Sanjeev Arora, James R. Lee, Assaf Naor |
| 2004 | FOCS | 0(sqrt (log n)) Approximation to SPARSEST CUT in (n | Sanjeev Arora, Elad Hazan, Satyen Kale |
| 2004 | STOC | Expander flows, geometric embeddings and graph partitioning. | Sanjeev Arora, Satish Rao, Umesh V. Vazirani |
| 2003 | FCT | Proving Integrality Gaps without Knowing the Linear Program. | Sanjeev Arora |
| 2003 | ICALP | Approximation Schemes for Degree-Restricted MST and Red-Blue Separation Problem. | Sanjeev Arora, Kevin L. Chang |
| 2002 | FOCS | Proving Integrality Gaps without Knowing the Linear Program. | Sanjeev Arora, Bla Bollobs, Lszl Lovsz |
| 2002 | SODA | A randomized online algorithm for bandwidth utilization. | Sanjeev Arora, Bo Brinkman |
| 2002 | STOC | Fitting algebraic curves to noisy data. | Sanjeev Arora, Subhash Khot |
| 2001 | STOC | Learning mixtures of arbitrary gaussians. | Sanjeev Arora, Ravi Kannan |
| 2000 | SODA | A 2+epsilon approximation algorithm for the | Sanjeev Arora, George Karakostas |
| 1999 | SODA | Page Replacement for General Caching Problems. | Susanne Albers, Sanjeev Arora, Sanjeev Khanna |
| 1999 | STOC | Approximation Schemes for Minimum Latency Problems. | Sanjeev Arora, George Karakostas |
| 1998 | SODA | A Polynomial-Time Approximation Scheme for Weighted Planar Graph TSP. | Sanjeev Arora, Michelangelo Grigni, David R. Karger, Philip N. Klein, Andrzej Woloszyn |
| 1998 | STOC | The Approximability of NP-hard Problems. | Sanjeev Arora |
| 1998 | STOC | Approximation Schemes for Euclidean | Sanjeev Arora, Prabhakar Raghavan, Satish Rao |
| 1997 | FOCS | Nearly Linear Time Approximation Schemes for Euclidean TSP and other Geometric Problems. | Sanjeev Arora |
| 1997 | STOC | Improved Low-Degree Testing and its Applications. | Sanjeev Arora, Madhu Sudan |
| 1996 | FOCS | Polynomial Time Approximation Schemes for Euclidean TSP and Other Geometric Problems. | Sanjeev Arora |
| 1996 | FOCS | A New Rounding Procedure for the Assignment Problem with Applications to Dense Graph Arrangement Problems. | Sanjeev Arora, Alan M. Frieze, Haim Kaplan |
| 1995 | FOCS | Reductions, Codes, PCPs, and Inapproximability. | Sanjeev Arora |
| 1995 | STOC | Polynomial time approximation schemes for dense instances of | Sanjeev Arora, David R. Karger, Marek Karpinski |
| 1994 | STOC | Simulating quadratic dynamical systems is PSPACE-complete (preliminary version). | Sanjeev Arora, Yuval Rabani, Umesh V. Vazirani |
| 1993 | FOCS | The Hardness of Approximate Optimia in Lattices, Codes, and Systems of Linear Equations | Sanjeev Arora, Lszl Babai, Jacques Stern, Z. Sweedyk |
| 1992 | FOCS | Proof Verification and Hardness of Approximation Problems | Sanjeev Arora, Carsten Lund, Rajeev Motwani, Madhu Sudan, Mario Szegedy |
| 1992 | FOCS | Probabilistic Checking of Proofs; A New Characterization of NP | Sanjeev Arora, Shmuel Safra |
| 1990 | STOC | On-line Algorithms for Path Selection in a Nonblocking Network (Extended Abstract) | Sanjeev Arora, Frank Thomson Leighton, Bruce M. Maggs |