Tengyu Ma

verfied profile

∙ 0 followers
Princeton University ∙ Stanford University

Assistant Professor of Computer Science and Statistics at Stanford University

Data-dependent Sample Complexity of Deep Neural Networks via Lipschitz Augmentation

Existing Rademacher complexity bounds for neural networks rely only on n...
05/09/2019 ∙ by Colin Wei, et al. ∙ 20 ∙ share

read it
Bootstrapping the Expressivity with Model-based Planning

We compare the model-free reinforcement learning with the model-based ap...
10/14/2019 ∙ by Kefan Dong, et al. ∙ 16 ∙ share

read it
MOPO: Model-based Offline Policy Optimization

Offline reinforcement learning (RL) refers to the problem of learning po...
05/27/2020 ∙ by Tianhe Yu, et al. ∙ 15 ∙ share

read it
Optimal Regularization Can Mitigate Double Descent

Recent empirical and theoretical studies have shown that many learning a...
03/04/2020 ∙ by Preetum Nakkiran, et al. ∙ 13 ∙ share

read it
Variable-Viewpoint Representations for 3D Object Recognition

For the problem of 3D object recognition, researchers using deep learnin...
02/08/2020 ∙ by Tengyu Ma, et al. ∙ 12 ∙ share

read it
Model-based Adversarial Meta-Reinforcement Learning

Meta-reinforcement learning (meta-RL) aims to learn from multiple traini...
06/16/2020 ∙ by Zichuan Lin, et al. ∙ 11 ∙ share

read it
On the Performance of Thompson Sampling on Logistic Bandits

We study the logistic bandit, in which rewards are binary with success p...
05/12/2019 ∙ by Shi Dong, et al. ∙ 10 ∙ share

read it
Shape Matters: Understanding the Implicit Bias of the Noise Covariance

The noise in stochastic gradient descent (SGD) provides a crucial implic...
06/15/2020 ∙ by Jeff Z. HaoChen, et al. ∙ 9 ∙ share

read it
Active Online Domain Adaptation

Online machine learning systems need to adapt to domain shifts. Meanwhil...
06/25/2020 ∙ by Yining Chen, et al. ∙ 9 ∙ share

read it
Fixup Initialization: Residual Learning Without Normalization

Normalization layers are a staple in state-of-the-art deep neural networ...
01/27/2019 ∙ by Hongyi Zhang, et al. ∙ 8 ∙ share

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

The aim of multi-task reinforcement learning is two-fold: (1) efficientl...
07/11/2019 ∙ by Nicholas C. Landolfi, et al. ∙ 7 ∙ share

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

For linear classifiers, the relationship between (normalized) output mar...
10/09/2019 ∙ by Colin Wei, et al. ∙ 7 ∙ share

read it
Towards Explaining the Regularization Effect of Initial Large Learning Rate in Training Neural Networks

Stochastic gradient descent with a large initial learning rate is a wide...
07/10/2019 ∙ by Yuanzhi Li, et al. ∙ 6 ∙ share

read it
The Implicit and Explicit Regularization Effects of Dropout

Dropout is a widely-used regularization technique, often required to obt...
02/28/2020 ∙ by Colin Wei, et al. ∙ 6 ∙ share

read it
Understanding Self-Training for Gradual Domain Adaptation

Machine learning systems must adapt to data distributions that evolve ov...
02/26/2020 ∙ by Ananya Kumar, et al. ∙ 5 ∙ share

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

Imitation learning, followed by reinforcement learning algorithms, is a ...
07/12/2019 ∙ by Yuping Luo, et al. ∙ 2 ∙ share

read it
Verified Uncertainty Calibration

Applications such as weather forecasting and personalized medicine deman...
09/23/2019 ∙ by Ananya Kumar, et al. ∙ 2 ∙ share

read it
Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss

Deep learning algorithms can fare poorly when the training dataset suffe...
06/18/2019 ∙ by Kaidi Cao, et al. ∙ 1 ∙ share

read it
On the Optimization Landscape of Tensor Decompositions

Non-convex optimization with local search heuristics has been widely use...
06/18/2017 ∙ by Rong Ge, et al. ∙ 0 ∙ share

read it
Generalization and Equilibrium in Generative Adversarial Nets (GANs)

We show that training of generative adversarial network (GAN) may not ha...
03/02/2017 ∙ by Sanjeev Arora, et al. ∙ 0 ∙ share

read it
Provable learning of Noisy-or Networks

Many machine learning applications use latent variable models to explain...
12/28/2016 ∙ by Sanjeev Arora, et al. ∙ 0 ∙ share

read it
Identity Matters in Deep Learning

An emerging design principle in deep learning is that each layer of a de...
11/14/2016 ∙ by Moritz Hardt, et al. ∙ 0 ∙ share

read it
Finding Approximate Local Minima Faster than Gradient Descent

We design a non-convex second-order optimization algorithm that is guara...
11/03/2016 ∙ by Naman Agarwal, et al. ∙ 0 ∙ share

read it
A Non-generative Framework and Convex Relaxations for Unsupervised Learning

We give a novel formal theoretical framework for unsupervised learning w...
10/04/2016 ∙ by Elad Hazan, et al. ∙ 0 ∙ share

read it
Gradient Descent Learns Linear Dynamical Systems

We prove that gradient descent efficiently converges to the global optim...
09/16/2016 ∙ by Moritz Hardt, et al. ∙ 0 ∙ share

read it
Provable Algorithms for Inference in Topic Models

Recently, there has been considerable progress on designing algorithms w...
05/27/2016 ∙ by Sanjeev Arora, et al. ∙ 0 ∙ share

read it
Matrix Completion has No Spurious Local Minimum

Matrix completion is a basic machine learning problem that has wide appl...
05/24/2016 ∙ by Rong Ge, et al. ∙ 0 ∙ share

read it
Communication Lower Bounds for Statistical Estimation Problems via a Distributed Data Processing Inequality

We study the tradeoff between the statistical error and communication co...
06/24/2015 ∙ by Mark Braverman, et al. ∙ 0 ∙ share

read it
Decomposing Overcomplete 3rd Order Tensors using Sum-of-Squares Algorithms

Tensor rank and low-rank tensor decompositions have many applications in...
04/21/2015 ∙ by Rong Ge, et al. ∙ 0 ∙ share

read it
Simple, Efficient, and Neural Algorithms for Sparse Coding

Sparse coding is a basic task in many fields including signal processing...
03/02/2015 ∙ by Sanjeev Arora, et al. ∙ 0 ∙ share

read it
More Algorithms for Provable Dictionary Learning

In dictionary learning, also known as sparse coding, the algorithm is gi...
01/03/2014 ∙ by Sanjeev Arora, et al. ∙ 0 ∙ share

read it
Linear Algebraic Structure of Word Senses, with Applications to Polysemy

Word embeddings are ubiquitous in NLP and information retrieval, but it'...
01/14/2016 ∙ by Sanjeev Arora, et al. ∙ 0 ∙ share

read it
RAND-WALK: A Latent Variable Model Approach to Word Embeddings

Semantic word embeddings represent the meaning of a word via a vector, a...
02/12/2015 ∙ by Sanjeev Arora, et al. ∙ 0 ∙ share

read it
Learning One-hidden-layer Neural Networks with Landscape Design

We consider the problem of learning a one-hidden-layer neural network: w...
11/01/2017 ∙ by Rong Ge, et al. ∙ 0 ∙ share

read it
Algorithmic Regularization in Over-parameterized Matrix Recovery

We study the problem of recovering a low-rank matrix X^ from linear meas...
12/26/2017 ∙ by Yuanzhi Li, et al. ∙ 0 ∙ share

read it
Algorithmic Regularization in Over-parameterized Matrix Sensing and Neural Networks with Quadratic Activations

We show that the (stochastic) gradient descent algorithm provides an imp...
12/26/2017 ∙ by Yuanzhi Li, et al. ∙ 0 ∙ share

read it
A La Carte Embedding: Cheap but Effective Induction of Semantic Feature Vectors

Motivations like domain adaptation, transfer learning, and feature learn...
05/14/2018 ∙ by Mikhail Khodak, et al. ∙ 0 ∙ share

read it
Seeing Neural Networks Through a Box of Toys: The Toybox Dataset of Visual Object Transformations

Deep convolutional neural networks (CNNs) have enjoyed tremendous succes...
06/15/2018 ∙ by Xiaohan Wang, et al. ∙ 0 ∙ share

read it
Approximability of Discriminators Implies Diversity in GANs

While Generative Adversarial Networks (GANs) have empirically produced i...
06/27/2018 ∙ by Yu Bai, et al. ∙ 0 ∙ share

read it
Algorithmic Framework for Model-based Reinforcement Learning with Theoretical Guarantees

While model-based reinforcement learning has empirically been shown to s...
07/10/2018 ∙ by Huazhe Xu, et al. ∙ 0 ∙ share

read it
Optimal Design of Process Flexibility for General Production Systems

Process flexibility is widely adopted as an effective strategy for respo...
06/07/2018 ∙ by Xi Chen, et al. ∙ 0 ∙ share

read it
On the Margin Theory of Feedforward Neural Networks

Past works have shown that, somewhat surprisingly, over-parametrization ...
10/12/2018 ∙ by Colin Wei, et al. ∙ 0 ∙ share

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

Memorization in over-parameterized neural networks could severely hurt g...
03/24/2020 ∙ by Jiaming Song, et al. ∙ 0 ∙ share

read it
Federated Accelerated Stochastic Gradient Descent

We propose Federated Accelerated Stochastic Gradient Descent (FedAc), a ...
06/16/2020 ∙ by Honglin Yuan, et al. ∙ 0 ∙ share

read it
Individual Calibration with Randomized Forecasting

Machine learning applications often require calibrated predictions, e.g....
06/18/2020 ∙ by Shengjia Zhao, et al. ∙ 0 ∙ share

read it
Self-training Avoids Using Spurious Features Under Domain Shift

In unsupervised domain adaptation, existing theory focuses on situations...
06/17/2020 ∙ by Yining Chen, et al. ∙ 0 ∙ share

read it
Simplifying Models with Unlabeled Output Data

We focus on prediction problems with high-dimensional outputs that are s...
06/29/2020 ∙ by Sang Michael Xie, et al. ∙ 0 ∙ share

read it
Heteroskedastic and Imbalanced Deep Learning with Adaptive Regularization

Real-world large-scale datasets are heteroskedastic and imbalanced – lab...
06/29/2020 ∙ by Kaidi Cao, et al. ∙ 0 ∙ share

read it

Tengyu Ma

Featured Co-authors