b'Song Mei'

DeepAI

Featured Co-authors

Caiming Xiong
183 publications
Andrea Montanari
73 publications
Huan Wang
59 publications
Bin Yu
58 publications
Chi Jin
53 publications
Yingbo Zhou
40 publications
Yu Bai
40 publications
David Gamarnik
33 publications
John Duchi
31 publications
Zhou Fan
22 publications
Fan Chen
16 publications

research

∙ 12/13/2022

A Novel Location Free Link Prediction in Multiplex Social Networks

In recent decades, the emergence of social networks has enabled internet...

Song Mei, et al. ∙

research

∙ 11/04/2022

Near-optimal multiple testing in Bayesian linear models with finite-sample FDR control

In high dimensional variable selection problems, statisticians often see...

Taejoo Ahn, et al. ∙

research

∙ 09/29/2022

Partially Observable RL with B-Stability: Unified Structural Condition and Sharp Sample-Efficient Algorithms

Partial Observability – where agents can only observe partial informatio...

Fan Chen, et al. ∙

research

∙ 09/23/2022

Unified Algorithms for RL with Decision-Estimation Coefficients: No-Regret, PAC, and Reward-Free Learning

Finding unified complexity measures and algorithms for sample-efficient ...

Fan Chen, et al. ∙

research

∙ 05/30/2022

Efficient Φ-Regret Minimization in Extensive-Form Games via Online Mirror Descent

A conceptually appealing approach for learning Extensive-Form Games (EFG...

Yu Bai, et al. ∙

research

∙ 05/15/2022

Sample-Efficient Learning of Correlated Equilibria in Extensive-Form Games

Imperfect-Information Extensive-Form Games (IIEFGs) is a prevalent model...

Ziang Song, et al. ∙

research

∙ 04/21/2022

Performance and limitations of the QAOA at constant levels on large sparse hypergraphs and spin glass models

The Quantum Approximate Optimization Algorithm (QAOA) is a general purpo...

Joao Basso, et al. ∙

research

∙ 02/22/2022

Efficient and Differentiable Conformal Prediction with General Function Classes

Quantifying the data uncertainty in learning tasks is often done by lear...

Yu Bai, et al. ∙

research

∙ 02/03/2022

Near-Optimal Learning of Extensive-Form Games with Imperfect Information

This paper resolves the open question of designing near-optimal algorith...

Yu Bai, et al. ∙

research

∙ 11/16/2021

Learning with convolution and pooling operations in kernel methods

Recent empirical work has shown that hierarchical convolutional kernels ...

Theodor Misiakiewicz, et al. ∙

research

∙ 11/13/2021

The Three Stages of Learning Dynamics in High-Dimensional Kernel Methods

To understand how deep learning works, it is crucial to understand the t...

Nikhil Ghosh, et al. ∙

research

∙ 10/08/2021

When Can We Learn General-Sum Markov Games with a Large Number of Players Sample-Efficiently?

Multi-agent reinforcement learning has made substantial empirical progre...

Ziang Song, et al. ∙

research

∙ 06/21/2021

Local convexity of the TAP free energy and AMP convergence for Z2-synchronization

We study mean-field variational Bayesian inference using the TAP approac...

Michael Celentano, et al. ∙

research

∙ 06/10/2021

Understanding the Under-Coverage Bias in Uncertainty Estimation

Estimating the data uncertainty in regression tasks is often done by lea...

Yu Bai, et al. ∙

research

∙ 03/08/2021

Exact Gap between Generalization Error and Uniform Convergence in Random Feature Models

Recent work showed that there could be a large gap between the classical...

Zitong Yang, et al. ∙

research

∙ 02/25/2021

Learning with invariances in random features and kernel models

A number of machine learning tasks entail a high degree of invariance: t...

Song Mei, et al. ∙

research

∙ 02/15/2021

Don't Just Blame Over-parametrization for Over-confidence: Theoretical Analysis of Calibration in Binary Classification

Modern machine learning models with high accuracy are often miscalibrate...

Yu Bai, et al. ∙

research

∙ 01/26/2021

Generalization error of random features and kernel methods: hypercontractivity and kernel matrix concentration

Consider the classical supervised learning problem: we are given data (y...

Song Mei, et al. ∙

research

∙ 06/24/2020

When Do Neural Networks Outperform Kernel Methods?

For a certain scaling of the initialization of stochastic gradient desce...

Behrooz Ghorbani, et al. ∙

research

∙ 08/14/2019

The generalization error of random features regression: Precise asymptotics and double descent curve

Deep learning methods operate in regimes that defy the traditional stati...

Song Mei, et al. ∙

research

∙ 06/21/2019

Limitations of Lazy Training of Two-layers Neural Networks

We study the supervised learning problem under either of the following t...

Behrooz Ghorbani, et al. ∙

research

∙ 04/27/2019

Linearized two-layers neural networks in high dimension

We consider the problem of learning an unknown function f_ on the d-dime...

Behrooz Ghorbani, et al. ∙

research

∙ 03/01/2019

Proximal algorithms for constrained composite optimization, with applications to solving low-rank SDPs

We study a family of (potentially non-convex) constrained optimization p...

Yu Bai, et al. ∙

research

∙ 02/16/2019

Mean-field theory of two-layers neural networks: dimension-free bounds and kernel limit

We consider learning two layer neural networks using stochastic gradient...

Song Mei, et al. ∙

research

∙ 08/23/2018

TAP free energy, spin glasses, and variational inference

We consider the Sherrington-Kirkpatrick model of spin glasses with ferro...

Zhou Fan, et al. ∙

research

∙ 04/18/2018

A Mean Field View of the Landscape of Two-Layers Neural Networks

Multi-layer neural networks are among the most powerful models in machin...

Song Mei, et al. ∙

research

∙ 11/15/2017

The landscape of the spiked tensor model

We consider the problem of estimating a large rank-one tensor u^⊗ k∈( R...

Gérard Ben Arous, et al. ∙

research

∙ 03/25/2017

Solving SDPs for synchronization and MaxCut problems via the Grothendieck inequality

A number of statistical estimation problems can be addressed by semidefi...

Song Mei, et al. ∙

research

∙ 07/22/2016

The Landscape of Empirical Risk for Non-convex Losses

Most high-dimensional estimation and prediction methods propose to minim...

Song Mei, et al. ∙