activity
20152023
most citedLearning One-hidden-layer Neural Networks with Landscape Design

112 citations · 289 across the 13 of their papers we have counts for

collaborators
Showing 2020Show all

13 papers · 1 filter

stat.ML2020

Beyond Lazy Training for Over-parameterized Tensor Decomposition

Xiang Wang, Chenwei Wu, Jason D. Lee +2

Over-parametrization is an important technique in training neural networks. In both theory and practice, training a larger network allows the optimization algorithm to avoid bad lo…

cs.LG2020

Sanity-Checking Pruning Methods: Random Tickets can Win the Jackpot

Jingtong Su, Yihang Chen, Tianle Cai +4

Network pruning is a method for reducing test-time computational resource requirements with minimal performance degradation. Conventional wisdom of pruning algorithms suggests that…

cs.LG2020

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

Yu Bai, Minshuo Chen, Pan Zhou +5

Meta-learning aims to perform fast adaptation on a new task through learning a "prior" from multiple existing tasks. A common practice in meta-learning is to perform a train-valida…

cs.LG2020★ 7 cited

Generalized Leverage Score Sampling for Neural Networks

Jason D. Lee, Ruoqi Shen, Zhao Song +2

Leverage score sampling is a powerful technique that originates from theoretical computer science, which can be used to speed up a large number of fundamental questions, e.g. linea…

cs.LG2020★ 7 cited

Implicit Bias in Deep Linear Classification: Initialization Scale vs Training Accuracy

Edward Moroshko, Suriya Gunasekar, Blake Woodworth +3

We provide a detailed asymptotic study of gradient flow trajectories and their implicit optimization bias when minimizing the exponential loss over "diagonal linear networks". This…

stat.ML2020

Modeling from Features: a Mean-field Framework for Over-parameterized Deep Neural Networks

Cong Fang, Jason D. Lee, Pengkun Yang +1

This paper proposes a new mean-field framework for over-parameterized deep neural networks (DNNs), which can be used to analyze neural network training. In this framework, a DNN is…