Fanghui Liu

À propos
Confidentialité
Mentions légales

Graph Chatbot

Publications associées (19)

What can online reinforcement learning with function approximation benefitfrom general coverage conditions

Volkan Cevher, Fanghui Liu, Luca Viano

2023

On the Convergence of Encoder-only Shallow Transformers

Volkan Cevher, Grigorios Chrysos, Fanghui Liu, Yongtao Wu

In this paper, we aim to build the global convergence theory of encoder-only shallow Transformers under a realistic setting from the perspective of architectures, initialization, and scaling under a finite width regime. The difficulty lies in how to tackle ...

2023

Benign Overfitting in Deep Neural Networks under Lazy Training

Volkan Cevher, Grigorios Chrysos, Fanghui Liu, Zhenyu Zhu

This paper focuses on over-parameterized deep neural networks (DNNs) with ReLU activation functions and proves that when the data distribution is well-separated, DNNs can achieve Bayesoptimal test error for classification while obtaining (nearly) zero-trai ...

2023

Extrapolation and Spectral Bias of Neural Nets with Hadamard Product: a Polynomial Net Study

Volkan Cevher, Grigorios Chrysos, Fanghui Liu, Zhenyu Zhu, Yongtao Wu

Neural tangent kernel (NTK) is a powerful tool to analyze training dynamics of neural networks and their generalization bounds. The study on NTK has been devoted to typical neural network architectures, but it is incomplete for neural networks with Hadamar ...

2022

Sound and Complete Verification of Polynomial Networks

Volkan Cevher, Grigorios Chrysos, Fanghui Liu, Mehmet Fatih Sahin, Elias Abad Rocamora

Polynomial Networks (PNs) have demonstrated promising performance on face and image recognition recently. However, robustness of PNs is unclear and thus obtaining certificates becomes imperative for enabling their adoption in real-world applications. Exist ...

2022

On the Double Descent of Random Features Models Trained with SGD

Volkan Cevher, Fanghui Liu

We study generalization properties of random features (RF) regression in high dimensions optimized by stochastic gradient descent (SGD) in under-/overparameterized regime. In this work, we derive precise non-asymptotic error bounds of RF regression under b ...

2022

Understanding Deep Neural Function Approximation in Reinforcement Learning via ϵ-Greedy Exploration

Volkan Cevher, Fanghui Liu, Luca Viano

This paper provides a theoretical study of deep neural function approximation in reinforcement learning (RL) with the ϵ-greedy exploration under the online setting. This problem setting is motivated by the successful deep Q-networks (DQN) framework that fa ...

2022

Robustness in deep learning: The good (width), the bad (depth), and the ugly (initialization)

Volkan Cevher, Grigorios Chrysos, Fanghui Liu, Zhenyu Zhu

We study the average robustness notion in deep neural networks in (selected) wide and narrow, deep and shallow, as well as lazy and non-lazy training settings. We prove that in the under-parameterized setting, width has a negative effect while it improves ...

2022

Generalization Properties of NAS under Activation and Skip Connection Search

Volkan Cevher, Grigorios Chrysos, Fanghui Liu, Zhenyu Zhu

Neural Architecture Search (NAS) has fostered the automatic discovery of stateof- the-art neural architectures. Despite the progress achieved with NAS, so far there is little attention to theoretical guarantees on NAS. In this work, we study the generaliza ...

2022

Page 2 sur 2