b'Sham Kakade'

research

∙ 09/07/2023

Pareto Frontiers in Neural Feature Learning: Data, Compute, Width, and Luck

This work investigates the nuanced algorithm design choices for deep lea...

0 Benjamin L. Edelman, et al. ∙

research

∙ 07/18/2023

Scaling Laws for Imitation Learning in NetHack

Imitation Learning (IL) is one of the most widely used methods in machin...

0 Jens Tuyls, et al. ∙

research

∙ 06/14/2023

Beyond Implicit Bias: The Insignificance of SGD Noise in Online Learning

The success of SGD in deep learning has been ascribed by prior works to ...

0 Nikhil Vyas, et al. ∙

research

∙ 05/30/2023

AdANNS: A Framework for Adaptive Semantic Search

Web-scale search systems learn an encoder to embed a given query which i...

0 Aniket Rege, et al. ∙

research

∙ 05/18/2023

Modified Gauss-Newton Algorithms under Noise

Gauss-Newton methods and their stochastic version have been widely used ...

0 Krishna Pillutla, et al. ∙

research

∙ 02/21/2023

Provable Copyright Protection for Generative Models

There is a growing concern that learned conditional generative models ma...

0 Nikhil Vyas, et al. ∙

research

∙ 09/01/2022

Recurrent Convolutional Neural Networks Learn Succinct Learning Algorithms

Neural Networks (NNs) struggle to efficiently learn certain problems, su...

0 Surbhi Goel, et al. ∙

research

∙ 07/18/2022

Hidden Progress in Deep Learning: SGD Learns Parities Near the Computational Limit

There is mounting empirical evidence of emergent phenomena in the capabi...

0 Boaz Barak, et al. ∙

research

∙ 05/26/2022

Matryoshka Representations for Adaptive Deployment

Learned representations are a central component in modern ML systems, se...

10 Aditya Kusupati, et al. ∙

research

∙ 03/08/2022

A Sharp Characterization of Linear Estimators for Offline Policy Evaluation

Offline policy evaluation is a fundamental statistical problem in reinfo...

0 Juan C. Perdomo, et al. ∙

research

∙ 02/28/2022

Understanding Contrastive Learning Requires Incorporating Inductive Biases

Contrastive learning is a popular form of self-supervised learning that ...

35 Nikunj Saunshi, et al. ∙

research

∙ 01/04/2022

Multi-Stage Episodic Control for Strategic Exploration in Text Games

Text adventure games present unique challenges to reinforcement learning...

3 Jens Tuyls, et al. ∙

research

∙ 10/21/2021

Anti-Concentrated Confidence Bonuses for Scalable Exploration

Intrinsic rewards play a central role in handling the exploration-exploi...

0 Jordan T. Ash, et al. ∙

research

∙ 10/19/2021

Inductive Biases and Variable Creation in Self-Attention Mechanisms

Self-attention, an architectural motif designed to model long-range inte...

0 Benjamin L. Edelman, et al. ∙

research

∙ 10/12/2021

Sparsity in Partially Controllable Linear Systems

A fundamental concept in control theory is that of controllability, wher...

0 Yonathan Efroni, et al. ∙

research

∙ 06/30/2021

Koopman Spectrum Nonlinear Regulator and Provably Efficient Online Learning

Most modern reinforcement learning algorithms optimize a cumulative sing...

0 Motoya Ohnishi, et al. ∙

research

∙ 06/17/2021

Gone Fishing: Neural Active Learning with Fisher Embeddings

There is an increasing need for effective active learning algorithms tha...

0 Jordan T. Ash, et al. ∙

research

∙ 06/02/2021

LLC: Accurate, Multi-purpose Learnt Low-dimensional Binary Codes

Learning binary representations of instances and classes is a classical ...

8 Aditya Kusupati, et al. ∙

research

∙ 02/18/2021

Robust and Differentially Private Mean Estimation

Differential privacy has emerged as a standard requirement in a variety ...

0 Xiyang Liu, et al. ∙

research

∙ 10/12/2020

How Important is the Train-Validation Split in Meta-Learning?

Meta-learning aims to perform fast adaptation on a new task through lear...

10 Yu Bai, et al. ∙

research

∙ 07/16/2020

PC-PG: Policy Cover Directed Exploration for Provable Policy Gradient Learning

Direct policy gradient methods for reinforcement learning are a successf...

0 Alekh Agarwal, et al. ∙

research

∙ 06/22/2020

Information Theoretic Regret Bounds for Online Nonlinear Control

This work studies the problem of sequential control in an unknown, nonli...

14 Sham Kakade, et al. ∙

research

∙ 06/18/2020

FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs

In order to deal with the curse of dimensionality in reinforcement learn...

7 Alekh Agarwal, et al. ∙

research

∙ 06/17/2020

Robust Meta-learning for Mixed Linear Regression with Small Batches

A common challenge faced in practical supervised learning, such as medic...

29 Weihao Kong, et al. ∙

research

∙ 04/07/2020

PACT: Privacy Sensitive Protocols and Mechanisms for Mobile Contact Tracing

The global health threat from COVID-19 has been controlled in a number o...

0 Justin Chan, et al. ∙

research

∙ 03/04/2020

Optimal Regularization Can Mitigate Double Descent

Recent empirical and theoretical studies have shown that many learning a...

13 Preetum Nakkiran, et al. ∙

research

∙ 02/28/2020

The Implicit and Explicit Regularization Effects of Dropout

Dropout is a widely-used regularization technique, often required to obt...

6 Colin Wei, et al. ∙

research

∙ 02/24/2020

Provable Representation Learning for Imitation Learning via Bi-level Optimization

A common strategy in modern learning systems is to learn a representatio...

6 Sanjeev Arora, et al. ∙

research

∙ 02/20/2020

Meta-learning for mixed linear regression

In modern supervised learning, there are a large number of tasks, but ma...

6 Weihao Kong, et al. ∙

research

∙ 02/08/2020

Soft Threshold Weight Reparameterization for Learnable Sparsity

Sparsity in Deep Neural Networks (DNNs) is studied extensively with the ...

3 Aditya Kusupati, et al. ∙

research

∙ 09/10/2019

Meta-Learning with Implicit Gradients

A core capability of intelligent systems is the ability to quickly learn...

2 Aravind Rajeswaran, et al. ∙

research

∙ 06/10/2019

On the Optimality of Sparse Model-Based Planning for Markov Decision Processes

This work considers the sample complexity of obtaining an ϵ-optimal poli...

0 Alekh Agarwal, et al. ∙

research

∙ 02/22/2019

Online Meta-Learning

A central capability of intelligent systems is the ability to continuous...

54 Chelsea Finn, et al. ∙

research

∙ 11/05/2018

Plan Online, Learn Offline: Efficient Learning and Exploration via Model-Based Control

We propose a plan online and learn offline (POLO) framework for the sett...

4 Kendall Lowrey, et al. ∙

research

∙ 09/23/2018

Provably Correct Automatic Subdifferentiation for Qualified Programs

The Cheap Gradient Principle (Griewank 2008) --- the computational cost ...

0 Sham Kakade, et al. ∙

research

∙ 04/20/2018

Stochastic subgradient method converges on tame functions

This work considers the question: what convergence guarantees does the s...

0 Damek Davis, et al. ∙

research

∙ 03/20/2018

Variance Reduction for Policy Gradient with Action-Dependent Factorized Baselines

Policy gradient methods have enjoyed great success in deep reinforcement...

0 Cathy Wu, et al. ∙

research

∙ 02/26/2018

Variance Reduction Methods for Sublinear Reinforcement Learning

This work considers the problem of provably optimal reinforcement learni...

0 Sham Kakade, et al. ∙

research

∙ 11/22/2017

Leverage Score Sampling for Faster Accelerated Regression and ERM

Given a matrix A∈R^n× d and a vector b ∈R^d, we show how to compute an ϵ...

0 Naman Agarwal, et al. ∙

research

∙ 11/07/2017

Learning Overcomplete HMMs

We study the problem of learning overcomplete HMMs---those that have man...

0 Vatsal Sharan, et al. ∙

research

∙ 12/08/2016

Prediction with a Short Memory

We consider the problem of predicting the next observation given a seque...

0 Sham Kakade, et al. ∙

research

∙ 06/08/2015

Convergence Rates of Active Learning for Maximum Likelihood Estimation

An active learner is given a class of models, a large set of unlabeled e...

0 Kamalika Chaudhuri, et al. ∙

research

∙ 02/13/2015

A Linear Dynamical System Model for Text

Low dimensional representations of words allow accurate NLP models to be...

0 David Belanger, et al. ∙

research

∙ 08/13/2013

When are Overcomplete Topic Models Identifiable? Uniqueness of Tensor Tucker Decompositions with Structured Sparsity

Overcomplete latent representations have been very popular for unsupervi...

0 Daniel Hsu, et al. ∙

research

∙ 02/20/2012

(weak) Calibration is Computationally Hard

We show that the existence of a computationally efficient calibration al...

0 Elad Hazan, et al. ∙

research

∙ 10/19/2011

An Optimal Algorithm for Linear Bandits

We provide the first algorithm for online bandit linear optimization who...

0 Nicolò Cesa-Bianchi, et al. ∙

research

∙ 04/11/2011

Efficient Learning of Generalized Linear and Single Index Models with Isotonic Regression

Generalized Linear Models (GLMs) and Single Index Models (SIMs) provide ...

0 Sham Kakade, et al. ∙

research

∙ 02/27/2010

Learning from Logged Implicit Exploration Data

We provide a sound and consistent foundation for the use of nonrandom ex...

0 Alex Strehl, et al. ∙

Sham Kakade

Featured Co-authors