
Representation Matters: Assessing the Importance of Subgroup Allocations in Training Data
Collecting more diverse and representative training data is often touted...
read it

Patterns, predictions, and actions: A story about machine learning
This graduate textbook on machine learning tells a story of how patterns...
read it

Interpolating Classifiers Make Few Mistakes
This paper provides elementary analyses of the regret and generalization...
read it

Towards Robust DataDriven Control Synthesis for Nonlinear Systems with Actuation Uncertainty
Modern nonlinear control theory seeks to endow systems with properties s...
read it

Do Offline Metrics Predict Online Performance in Recommender Systems?
Recommender systems operate in an inherently dynamical setting. Past rec...
read it

Guaranteeing Safety of Learned Perception Modules via MeasurementRobust Control Barrier Functions
Modern nonlinear control theory seeks to develop feedback controllers th...
read it

A Generalizable and Accessible Approach to Machine Learning with Global Satellite Imagery
Combining satellite imagery with machine learning (SIML) has the potenti...
read it

Certainty Equivalent PerceptionBased Control
In order to certify performance and safety, feedback control requires pr...
read it

Finding Equilibrium in MultiAgent Games with Payoff Uncertainty
We study the problem of finding equilibrium strategies in multiagent ga...
read it

Measuring Robustness to Natural Distribution Shifts in Image Classification
We study how robust current ImageNet models are to distribution shifts a...
read it

Active Learning for Nonlinear System Identification with Guarantees
While the identification of nonlinear dynamical systems is a fundamental...
read it

The Effect of Natural Distribution Shift on Question Answering Models
We build four new test sets for the Stanford Question Answering Dataset ...
read it

PostEstimation Smoothing: A Simple Baseline for Learning with Side Information
Observational data are often accompanied by natural structural indices, ...
read it

Neural Kernels Without Tangents
We investigate the connections between neural networks and simple buildi...
read it

Recommendations and User Agency: The Reachability of CollaborativelyFiltered Information
Recommender systems often rely on models which are trained to maximize a...
read it

Robust Guarantees for PerceptionBased Control
Motivated by vision based control of autonomous vehicles, we consider th...
read it

A systematic framework for natural perturbations from videos
We introduce a systematic framework for quantifying the robustness of cl...
read it

Finitetime Analysis of Approximate Policy Iteration for the Linear Quadratic Regulator
We study the sample complexity of approximate policy iteration (PI) for ...
read it

Model Similarity Mitigates Test Set Overuse
Excessive reuse of test data has become commonplace in today's machine l...
read it

Certainty Equivalent Control of LQR is Efficient
We study the performance of the certainty equivalent controller on the L...
read it

Learning Linear Dynamical Systems with SemiParametric Least Squares
We analyze a simple prefiltered variation of the least squares estimator...
read it

The Gap Between ModelBased and ModelFree Methods on the Linear Quadratic Regulator: An Asymptotic Viewpoint
The effectiveness of modelbased versus modelfree methods is a longsta...
read it

numpywren: serverless linear algebra
Linear algebra operations are widely used in scientific computing and ma...
read it

Massively Parallel Hyperparameter Tuning
Modern learning models are characterized by large hyperparameter spaces....
read it

Minimax Lower Bounds for H_∞Norm Estimation
The problem of estimating the H_∞norm of an LTI system from noisy input...
read it

A SuccessiveElimination Approach to Adaptive Robotic Sensing
We study the adaptive sensing problem for the multiple source seeking pr...
read it

Safely Learning to Control the Constrained Linear Quadratic Regulator
We study the constrained linear quadratic regulator with unknown dynamic...
read it

A Tour of Reinforcement Learning: The View from Continuous Control
This manuscript surveys reinforcement learning from the perspective of o...
read it

Do CIFAR10 Classifiers Generalize to CIFAR10?
Machine learning is currently dominated by largely experimental work foc...
read it

Regret Bounds for Robust Adaptive Control of the Linear Quadratic Regulator
We consider adaptive control of the Linear Quadratic Regulator (LQR), wh...
read it

Tight Query Complexity Lower Bounds for PCA via Finite Sample Deformed Wigner Law
We prove a query complexity lower bound for approximating the top r dime...
read it

FiniteData Performance Guarantees for the OutputFeedback Control of an Unknown System
As the systems we control become more complex, firstprinciple modeling ...
read it

Simple random search provides a competitive approach to reinforcement learning
A common belief in modelfree reinforcement learning is that methods bas...
read it

Learning Without Mixing: Towards A Sharp Analysis of Linear System Identification
We prove that the ordinary leastsquares (OLS) estimator attains nearly ...
read it

LeastSquares Temporal Difference Learning for the Linear Quadratic Regulator
Reinforcement learning (RL) has been successfully used to solve many con...
read it

An example of how false conclusions could be made with personalized health tracking and suggestions for avoiding similar situations
Personalizing interventions and treatments is a necessity for optimal me...
read it

Ground Control to Major Tom: the importance of field surveys in remotely sensed data analysis
In this project, we build a modular, scalable system that can collect, s...
read it

Firstorder Methods Almost Always Avoid Saddle Points
We establish that firstorder methods avoid saddle points for almost all...
read it

On the Sample Complexity of the Linear Quadratic Regulator
This paper addresses the optimal control problem known as the Linear Qua...
read it

Flare Prediction Using Photospheric and Coronal Image Data
The precise physical process that triggers solar flares is not currently...
read it

Meaningless comparisons lead to false optimism in medical machine learning
A new trend in medicine is the use of algorithms to analyze big datasets...
read it

The Marginal Value of Adaptive Gradient Methods in Machine Learning
Adaptive optimization methods, which perform local optimization with a m...
read it

On the Gap Between StrictSaddles and True Convexity: An Omega(log d) Lower Bound for Eigenvector Approximation
We prove a query complexity lower bound on rankone principal component ...
read it

The Simulator: Understanding Adaptive Sampling in the ModerateConfidence Regime
We propose a novel technique for analyzing adaptive sampling called the ...
read it

Saturating Splines and Feature Selection
We extend the adaptive regression spline model by incorporating saturati...
read it

Gradient Descent Learns Linear Dynamical Systems
We prove that gradient descent efficiently converges to the global optim...
read it

CYCLADES: Conflictfree Asynchronous Machine Learning
We present CYCLADES, a general framework for parallelizing stochastic op...
read it

On kernel methods for covariates that are rankings
Permutationvalued features arise in a variety of applications, either i...
read it

BestofK Bandits
This paper studies the BestofK Bandit game: At each time the player ch...
read it

Large Scale Kernel Learning using Block Coordinate Descent
We demonstrate that distributed block coordinate descent can quickly sol...
read it