← Authors

Sham Kakade

65 papers · 2010–2025 · 9 conferences · across top CS/AI conferences

Achievements

🌈 Renaissance Researcher (6) πŸƒ Academic Marathon (15) πŸŒ‰ Interdisciplinary Bridge 🌍 Conference Polyglot (9) 🐝 Cross-Pollinator (13) 🐣 Hot Topic Early Bird πŸ—ΊοΈ Taxonomy Completionist (27) 🧭 Keyword Pioneer 🏠 Conference Loyalist (28) πŸ”¬ Deep Specialist (16) πŸ‘₯ Mega-Team (60) πŸ“ˆ Trend Setter ⚑ Prolific Year (7) πŸš€ Conference Pioneer πŸ’Ž Century Club (65) πŸ—ƒοΈ Keyword Collector (69) πŸ”₯ Unstoppable (9) ❓ The Questioner (3)

Conferences

NIPS (28) ICML (21) AISTATS (4) COLT (4) ALT (2) ICLR (2) JMLR (2) COLING (1) NAACL (1)

Top co-authors

Akshay Krishnamurthy (8) Cyril Zhang (8) Aditya Kusupati (7) Ali Farhadi (7) Prateek Jain (6) Surbhi Goel (6) Jingfeng Wu (5) Quanquan Gu (5) Difan Zou (5) Vladimir braverman (5)

Keywords

sample complexity (10) representation learning (6) stochastic gradient descent (5) domain adaptation (4) language model (4) transfer learning (4) linear regression (4) reinforcement learning (4) markov decision process (3) sample efficiency (3) linear dynamical system (3) spectral method (3) regret bound (3) neural network (3) image classification (2) empirical risk minimization (2) learning theory (2) computational complexity (2) model-based reinforcement learning (2) policy gradient (2)

Papers

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