b'Tengyu Ma'

research

∙ 06/16/2022

Max-Margin Works while Large Margin Fails: Generalization without Uniform Convergence

A major challenge in modern machine learning is theoretically understand...

Margalit Glasgow, et al. ∙

research

∙ 06/06/2022

Asymptotic Instance-Optimal Algorithms for Interactive Decision Making

Past research on interactive decision making problems (bandits, reinforc...

Kefan Dong, et al. ∙

research

∙ 05/22/2022

Near-Optimal Algorithms for Autonomous Exploration and Multi-Goal Stochastic Shortest Path

We revisit the incremental autonomous exploration problem proposed by Li...

Haoyuan Cai, et al. ∙

research

∙ 04/21/2022

Toward Fast, Flexible, and Robust Low-Light Image Enhancement

Existing low-light image enhancement techniques are mostly not only diff...

Long Ma, et al. ∙

research

∙ 04/06/2022

Beyond Separability: Analyzing the Linear Transferability of Contrastive Representations to Related Subpopulations

Contrastive learning is a highly effective method which uses unlabeled d...

Jeff Z. HaoChen, et al. ∙

research

∙ 04/01/2022

Connect, Not Collapse: Explaining Contrastive Learning for Unsupervised Domain Adaptation

We consider unsupervised domain adaptation (UDA), where labeled data fro...

Kendrick Shen, et al. ∙

research

∙ 02/21/2022

Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution

When transferring a pretrained model to a downstream task, two popular m...

Ananya Kumar, et al. ∙

research

∙ 02/15/2022

Safe Reinforcement Learning by Imagining the Near Future

Safe reinforcement learning is a promising path toward applying reinforc...

Garrett Thomas, et al. ∙

research

∙ 12/09/2021

Learning with Nested Scene Modeling and Cooperative Architecture Search for Low-Light Vision

Images captured from low-light scenes often suffer from severe degradati...

Risheng Liu, et al. ∙

research

∙ 12/09/2021

DR3: Value-Based Deep Reinforcement Learning Requires Explicit Regularization

Despite overparameterization, deep networks trained via supervised learn...

Aviral Kumar, et al. ∙

research

∙ 11/22/2021

Plan Better Amid Conservatism: Offline Multi-Agent Reinforcement Learning with Actor Rectification

The idea of conservatism has led to significant progress in offline rein...

Ling Pan, et al. ∙

research

∙ 11/03/2021

An Explanation of In-context Learning as Implicit Bayesian Inference

Large pretrained language models such as GPT-3 have the surprising abili...

Sang Michael Xie, et al. ∙

research

∙ 10/11/2021

Self-supervised Learning is More Robust to Dataset Imbalance

Self-supervised learning (SSL) is a scalable way to learn general visual...

Hong Liu, et al. ∙

research

∙ 08/04/2021

Learning Barrier Certificates: Towards Safe Reinforcement Learning with Zero Training-time Violations

Training-time safety violations have been a major concern when we deploy...

Yuping Luo, et al. ∙

research

∙ 07/28/2021

Statistically Meaningful Approximation: a Case Study on Approximating Turing Machines with Transformers

A common lens to theoretically study neural net architectures is to anal...

Colin Wei, et al. ∙

research

∙ 07/12/2021

Calibrating Predictions to Decisions: A Novel Approach to Multi-Class Calibration

When facing uncertainty, decision-makers want predictions they can trust...

Shengjia Zhao, et al. ∙

research

∙ 06/18/2021

Iterative Feature Matching: Toward Provable Domain Generalization with Logarithmic Environments

Domain generalization aims at performing well on unseen test environment...

Yining Chen, et al. ∙

research

∙ 06/17/2021

Why Do Pretrained Language Models Help in Downstream Tasks? An Analysis of Head and Prompt Tuning

Pretrained language models have achieved state-of-the-art performance wh...

Colin Wei, et al. ∙

research

∙ 06/11/2021

Label Noise SGD Provably Prefers Flat Global Minimizers

In overparametrized models, the noise in stochastic gradient descent (SG...

Alex Damian, et al. ∙

research

∙ 06/09/2021

Joint System-Wise Optimization for Pipeline Goal-Oriented Dialog System

Recent work (Takanobu et al., 2020) proposed the system-wise evaluation ...

Zichuan Lin, et al. ∙

research

∙ 06/08/2021

Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive Loss

Recent works in self-supervised learning have advanced the state-of-the-...

Jeff Z. HaoChen, et al. ∙

research

∙ 03/24/2021

Why Do Local Methods Solve Nonconvex Problems?

Non-convex optimization is ubiquitous in modern machine learning. Resear...

Tengyu Ma, et al. ∙

research

∙ 02/09/2021

Fine-Grained Gap-Dependent Bounds for Tabular MDPs via Adaptive Multi-Step Bootstrap

This paper presents a new model-free algorithm for episodic finite-horiz...

Haike Xu, et al. ∙

research

∙ 02/08/2021

Provable Model-based Nonlinear Bandit and Reinforcement Learning: Shelve Optimism, Embrace Virtual Curvature

This paper studies model-based bandit and reinforcement learning (RL) wi...

Kefan Dong, et al. ∙

research

∙ 12/08/2020

In-N-Out: Pre-Training and Self-Training using Auxiliary Information for Out-of-Distribution Robustness

Consider a prediction setting where a few inputs (e.g., satellite images...

Sang Michael Xie, et al. ∙

research

∙ 11/03/2020

Meta-learning Transferable Representations with a Single Target Domain

Recent works found that fine-tuning and joint training—two popular appro...

Hong Liu, et al. ∙

research

∙ 10/22/2020

Beyond Lazy Training for Over-parameterized Tensor Decomposition

Over-parametrization is an important technique in training neural networ...

Xiang Wang, et al. ∙

research

∙ 10/21/2020

Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Pooling

Document-level relation extraction (RE) poses new challenges compared to...

Wenxuan Zhou, et al. ∙

research

∙ 10/07/2020

Theoretical Analysis of Self-Training with Deep Networks on Unlabeled Data

Self-training algorithms, which train a model to fit pseudolabels predic...

Colin Wei, et al. ∙

research

∙ 08/27/2020

Entity and Evidence Guided Relation Extraction for DocRED

Document-level relation extraction is a challenging task which requires ...

Kevin Huang, et al. ∙

research

∙ 07/09/2020

Learning Over-Parametrized Two-Layer ReLU Neural Networks beyond NTK

We consider the dynamic of gradient descent for learning a two-layer neu...

Yuanzhi Li, et al. ∙

research

∙ 06/29/2020

Simplifying Models with Unlabeled Output Data

We focus on prediction problems with high-dimensional outputs that are s...

Sang Michael Xie, et al. ∙

research

∙ 06/29/2020

Heteroskedastic and Imbalanced Deep Learning with Adaptive Regularization

Real-world large-scale datasets are heteroskedastic and imbalanced – lab...

Kaidi Cao, et al. ∙

research

∙ 06/25/2020

Active Online Domain Adaptation

Online machine learning systems need to adapt to domain shifts. Meanwhil...

Yining Chen, et al. ∙

research

∙ 06/18/2020

Individual Calibration with Randomized Forecasting

Machine learning applications often require calibrated predictions, e.g....

Shengjia Zhao, et al. ∙

research

∙ 06/17/2020

Self-training Avoids Using Spurious Features Under Domain Shift

In unsupervised domain adaptation, existing theory focuses on situations...

Yining Chen, et al. ∙

research

∙ 06/16/2020

Federated Accelerated Stochastic Gradient Descent

We propose Federated Accelerated Stochastic Gradient Descent (FedAc), a ...

Honglin Yuan, et al. ∙

research

∙ 06/16/2020

Model-based Adversarial Meta-Reinforcement Learning

Meta-reinforcement learning (meta-RL) aims to learn from multiple traini...

Zichuan Lin, et al. ∙

research

∙ 06/15/2020

Shape Matters: Understanding the Implicit Bias of the Noise Covariance

The noise in stochastic gradient descent (SGD) provides a crucial implic...

Jeff Z. HaoChen, et al. ∙

research

∙ 05/27/2020

MOPO: Model-based Offline Policy Optimization

Offline reinforcement learning (RL) refers to the problem of learning po...

Tianhe Yu, et al. ∙

research

∙ 03/24/2020

Robust and On-the-fly Dataset Denoising for Image Classification

Memorization in over-parameterized neural networks could severely hurt g...

Jiaming Song, et al. ∙

research

∙ 03/04/2020

Optimal Regularization Can Mitigate Double Descent

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

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...

Colin Wei, et al. ∙

research

∙ 02/26/2020

Understanding Self-Training for Gradual Domain Adaptation

Machine learning systems must adapt to data distributions that evolve ov...

Ananya Kumar, et al. ∙

research

∙ 02/08/2020

Variable-Viewpoint Representations for 3D Object Recognition

For the problem of 3D object recognition, researchers using deep learnin...

Tengyu Ma, et al. ∙

research

∙ 10/14/2019

Bootstrapping the Expressivity with Model-based Planning

We compare the model-free reinforcement learning with the model-based ap...

Kefan Dong, et al. ∙

research

∙ 10/09/2019

Improved Sample Complexities for Deep Networks and Robust Classification via an All-Layer Margin

For linear classifiers, the relationship between (normalized) output mar...

Colin Wei, et al. ∙

research

∙ 09/23/2019

Verified Uncertainty Calibration

Applications such as weather forecasting and personalized medicine deman...

Ananya Kumar, et al. ∙

research

∙ 07/12/2019

Learning Self-Correctable Policies and Value Functions from Demonstrations with Negative Sampling

Imitation learning, followed by reinforcement learning algorithms, is a ...

Yuping Luo, et al. ∙

research

∙ 07/11/2019

A Model-based Approach for Sample-efficient Multi-task Reinforcement Learning

The aim of multi-task reinforcement learning is two-fold: (1) efficientl...

Nicholas C. Landolfi, et al. ∙

Tengyu Ma

Featured Co-authors