Sham Kakade

LoRA Soups: Merging LoRAs for Practical Skill Composition Tasks COLING 2025 A Study on the Calibration of In-context Learning NAACL 2024 CoLoR-Filter: Conditional Loss Reduction Filtering for Targeted Language Model Pre-training NeurIPS 2024 DataComp-LM: In search of the next generation of training sets for language models NeurIPS 2024 From an Image to a Scene: Learning to Imagine the World from a Million 360° Videos NeurIPS 2024 MatFormer: Nested Transformer for Elastic Inference NeurIPS 2024 Superposed Decoding: Multiple Generations from a Single Autoregressive Inference Pass NeurIPS 2024 Transcendence: Generative Models Can Outperform The Experts That Train Them NeurIPS 2024 A Complete Characterization of Linear Estimators for Offline Policy Evaluation JMLR 2023 AdANNS: A Framework for Adaptive Semantic Search NeurIPS 2023 Learning Hidden Markov Models Using Conditional Samples COLT 2023 Pareto Frontiers in Deep Feature Learning: Data, Compute, Width, and Luck NeurIPS 2023 Hidden Progress in Deep Learning: SGD Learns Parities Near the Computational Limit NeurIPS 2022 Inductive Biases and Variable Creation in Self-Attention Mechanisms ICML 2022 Last Iterate Risk Bounds of SGD with Decaying Stepsize for Overparameterized Linear Regression ICML 2022 Matryoshka Representation Learning NeurIPS 2022 Recurrent Convolutional Neural Networks Learn Succinct Learning Algorithms NeurIPS 2022 Risk Bounds of Multi-Pass SGD for Least Squares in the Interpolation Regime NeurIPS 2022 Sparsity in Partially Controllable Linear Systems ICML 2022 The Power and Limitation of Pretraining-Finetuning for Linear Regression under Covariate Shift NeurIPS 2022 Understanding Contrastive Learning Requires Incorporating Inductive Biases ICML 2022 Unpacking Reward Shaping: Understanding the Benefits of Reward Engineering on Sample Complexity NeurIPS 2022 An Exponential Lower Bound for Linearly Realizable MDP with Constant Suboptimality Gap NeurIPS 2021 Benign Overfitting of Constant-Stepsize SGD for Linear Regression COLT 2021 Bilinear Classes: A Structural Framework for Provable Generalization in RL ICML 2021 Going Beyond Linear RL: Sample Efficient Neural Function Approximation NeurIPS 2021 Gone Fishing: Neural Active Learning with Fisher Embeddings NeurIPS 2021 How Important is the Train-Validation Split in Meta-Learning? ICML 2021 Instabilities of Offline RL with Pre-Trained Neural Representation ICML 2021 LLC: Accurate, Multi-purpose Learnt Low-dimensional Binary Codes NeurIPS 2021 Optimal Gradient-based Algorithms for Non-concave Bandit Optimization NeurIPS 2021 Robust and differentially private mean estimation NeurIPS 2021 The Benefits of Implicit Regularization from SGD in Least Squares Problems NeurIPS 2021 Calibration, Entropy Rates, and Memory in Language Models ICML 2020 FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs NeurIPS 2020 Information Theoretic Regret Bounds for Online Nonlinear Control NeurIPS 2020 Is Long Horizon RL More Difficult Than Short Horizon RL? NeurIPS 2020 Leverage Score Sampling for Faster Accelerated Regression and ERM ALT 2020 Meta-learning for Mixed Linear Regression ICML 2020 Model-Based Multi-Agent RL in Zero-Sum Markov Games with Near-Optimal Sample Complexity NeurIPS 2020 Model-Based Reinforcement Learning with a Generative Model is Minimax Optimal COLT 2020 PC-PG: Policy Cover Directed Exploration for Provable Policy Gradient Learning NeurIPS 2020 Provable Representation Learning for Imitation Learning via Bi-level Optimization ICML 2020 Robust Meta-learning for Mixed Linear Regression with Small Batches NeurIPS 2020 Sample-Efficient Reinforcement Learning of Undercomplete POMDPs NeurIPS 2020 Soft Threshold Weight Reparameterization for Learnable Sparsity ICML 2020 The Implicit and Explicit Regularization Effects of Dropout ICML 2020 The Nonstochastic Control Problem ALT 2020 Maximum Likelihood Estimation for Learning Populations of Parameters ICML 2019 Online Control with Adversarial Disturbances ICML 2019 Online Meta-Learning ICML 2019 Plan Online, Learn Offline: Efficient Learning and Exploration via Model-Based Control ICLR 2019 Provably Efficient Maximum Entropy Exploration ICML 2019 Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulator ICML 2018 Variance Reduction for Policy Gradient with Action-Dependent Factorized Baselines ICLR 2018 Global Convergence of Non-Convex Gradient Descent for Computing Matrix Squareroot AISTATS 2017 A Linear Dynamical System Model for Text ICML 2015 Un-regularizing: approximate proximal point and faster stochastic algorithms for empirical risk minimization ICML 2015 When Are Overcomplete Topic Models Identifiable? Uniqueness of Tensor Tucker Decompositions with Structured Sparsity JMLR 2015 Least Squares Revisited: Scalable Approaches for Multi-class Prediction ICML 2014 A Tensor Spectral Approach to Learning Mixed Membership Community Models COLT 2013 Learning Linear Bayesian Networks with Latent Variables ICML 2013 Domain Adaptation: A Small Sample Statistical Approach AISTATS 2012 Domain Adaptation with Coupled Subspaces AISTATS 2011 Learning Exponential Families in High-Dimensions: Strong Convexity and Sparsity AISTATS 2010