ICLR

FastSpeech 2: Fast and High-Quality End-to-End Text to Speech

Yi Ren, Chenxu Hu, Xu Tan, Tao Qin, Sheng Zhao, Zhou Zhao, Tie-Yan Liu

Comments Accepted by ICLR 2021

Efficiently Modeling Long Sequences with Structured State Spaces

Albert Gu, Karan Goel, Christopher Ré

Comments ICLR 2022 (Outstanding Paper HM)

On the Convergence of the Monte Carlo Exploring Starts Algorithm for Reinforcement Learning

Che Wang, Shuhan Yuan, Kai Shao, Keith Ross

Comments The Tenth International Conference on Learning Representations. ICLR 2022. 33 pages

ZeroFL: Efficient On-Device Training for Federated Learning with Local Sparsity

Xinchi Qiu, Javier Fernandez-Marques, Pedro PB Gusmao, Yan Gao, Titouan Parcollet, Nicholas Donald Lane

Comments Published as a conference paper at ICLR 2022

Journal ref International Conference on Learning Representations, 2022

On the Connection between Local Attention and Dynamic Depth-wise Convolution

Qi Han, Zejia Fan, Qi Dai, Lei Sun, Ming-Ming Cheng, Jiaying Liu, Jingdong Wang

Comments ICLR 2022 Spotlight

On the Pitfalls of Analyzing Individual Neurons in Language Models

Omer Antverg, Yonatan Belinkov

Comments ICLR 2022 Main Conference

Towards Bridging the gap between Empirical and Certified Robustness against Adversarial Examples

Jay Nandy, Sudipan Saha, Wynne Hsu, Mong Li Lee, Xiao Xiang Zhu

Comments An abridged version of this work has been presented at ICLR 2021 Workshop on Security and Safety in Machine Learning Systems: https://aisecure-workshop.github.io/aml-iclr2021/papers/2.pdf

What Happens after SGD Reaches Zero Loss? --A Mathematical Framework

Zhiyuan Li, Tianhao Wang, Sanjeev Arora

Comments 56 pages, 2 figures; ICLR 2022

Versatile Weight Attack via Flipping Limited Bits

Jiawang Bai, Baoyuan Wu, Zhifeng Li, Shu-tao Xia

Comments Extension of our ICLR 2021 work: arXiv:2102.10496

Sound and Complete Neural Network Repair with Minimality and Locality Guarantees

Feisi Fu, Wenchao Li

Comments 17 pages, 3 figures

Journal ref International Conference on Learning Representations, 2022

An Explanation of In-context Learning as Implicit Bayesian Inference

Sang Michael Xie, Aditi Raghunathan, Percy Liang, Tengyu Ma

Comments ICLR 2022

How Well Does Self-Supervised Pre-Training Perform with Streaming Data?

Dapeng Hu, Shipeng Yan, Qizhengqiu Lu, Lanqing Hong, Hailin Hu, Yifan Zhang, Zhenguo Li, Xinchao Wang, Jiashi Feng

Comments Accepted to ICLR 2022

Align-Deform-Subtract: An Interventional Framework for Explaining Object Differences

Cian Eastwood, Li Nanbo, Christopher K. I. Williams

Comments ICLR 2022 Workshop on Objects, Structure and Causality

Implicit Gradient Regularization

David G. T. Barrett, Benoit Dherin

Comments Correction to formula A.14 in Appendix A.1 and update to the acknowledgments

Journal ref Published as a conference paper at ICLR 2021

Repairing Systematic Outliers by Learning Clean Subspaces in VAEs

Simao Eduardo, Kai Xu, Alfredo Nazabal, Charles Sutton

Comments Submitted for review in ICLR 2022

Anomalous behaviour in loss-gradient based interpretability methods

Vinod Subramanian, Siddharth Gururani, Emmanouil Benetos, Mark Sandler

Comments Accepted at ICLR RobustML workshop 2021

PER-ETD: A Polynomially Efficient Emphatic Temporal Difference Learning Method

Ziwei Guan, Tengyu Xu, Yingbin Liang

Comments Published as a conference paper at ICLR 2022

Differentially Private Fine-tuning of Language Models

Da Yu, Saurabh Naik, Arturs Backurs, Sivakanth Gopi, Huseyin A. Inan, Gautam Kamath, Janardhan Kulkarni, Yin Tat Lee, Andre Manoel, Lukas Wutschitz, Sergey Yekhanin, Huishuai Zhang

Comments ICLR 2022. Code available at https://github.com/huseyinatahaninan/Differentially-Private-Fine-tuning-of-Language-Models

RelaxLoss: Defending Membership Inference Attacks without Losing Utility

Dingfan Chen, Ning Yu, Mario Fritz

Comments International Conference on Learning Representations (ICLR) 2022, 28 pages

Journal ref International Conference on Learning Representations 2022

Model-Based Offline Meta-Reinforcement Learning with Regularization

Sen Lin, Jialin Wan, Tengyu Xu, Yingbin Liang, Junshan Zhang

Comments Published as a conference paper at ICLR 2022

On Bridging Generic and Personalized Federated Learning for Image Classification

Hong-You Chen, Wei-Lun Chao

Comments Accepted to International Conference on Learning Representations 2022 (ICLR 2022)

How to Train Your MAML to Excel in Few-Shot Classification

Han-Jia Ye, Wei-Lun Chao

Comments Accepted to International Conference on Learning Representations 2022 (ICLR 2022)

Efficient Self-supervised Vision Transformers for Representation Learning

Chunyuan Li, Jianwei Yang, Pengchuan Zhang, Mei Gao, Bin Xiao, Xiyang Dai, Lu Yuan, Jianfeng Gao

Comments ICLR 2022; Code: https://github.com/microsoft/esvit

Improving exploration in policy gradient search: Application to symbolic optimization

Mikel Landajuela, Brenden K. Petersen, Soo K. Kim, Claudio P. Santiago, Ruben Glatt, T. Nathan Mundhenk, Jacob F. Pettit, Daniel M. Faissol

Comments Published in 1st Mathematical Reasoning in General Artificial Intelligence Workshop, ICLR 2021

Journal ref 1st Mathematical Reasoning in General Artificial Intelligence Workshop, ICLR 2021

Distilling Wikipedia mathematical knowledge into neural network models

Joanne T. Kim, Mikel Landajuela, Brenden K. Petersen

Comments 6 pages, 4 figures

Journal ref 1st Mathematical Reasoning in General Artificial Intelligence Workshop, ICLR 2021

Deep symbolic regression: Recovering mathematical expressions from data via risk-seeking policy gradients

Brenden K. Petersen, Mikel Landajuela, T. Nathan Mundhenk, Claudio P. Santiago, Soo K. Kim, Joanne T. Kim

Comments Published at International Conference on Learning Representations, 2021

Journal ref International Conference on Learning Representations, 2021

Modular Lifelong Reinforcement Learning via Neural Composition

Jorge A. Mendez, Harm van Seijen, Eric Eaton

Comments Published at ICLR 2022. Code: https://github.com/Lifelong-ML/Mendez2022ModularLifelongRL

Language model compression with weighted low-rank factorization

Yen-Chang Hsu, Ting Hua, Sungen Chang, Qian Lou, Yilin Shen, Hongxia Jin

Comments ICLR 2022

On Non-Random Missing Labels in Semi-Supervised Learning

Xinting Hu, Yulei Niu, Chunyan Miao, Xian-Sheng Hua, Hanwang Zhang

Journal ref ICLR 2022

GDA-AM: On the effectiveness of solving minimax optimization via Anderson Acceleration

Huan He, Shifan Zhao, Yuanzhe Xi, Joyce C Ho, Yousef Saad

Comments 31 Pages, ICLR, minimax, Anderson Acceleration