Timezone: »
Poster
Zeroth-Order Stochastic Variance Reduction for Nonconvex Optimization
Sijia Liu · Bhavya Kailkhura · Pin-Yu Chen · Paishun Ting · Shiyu Chang · Lisa Amini
As application demands for zeroth-order (gradient-free) optimization accelerate, the need for variance reduced and faster converging approaches is also intensifying. This paper addresses these challenges by presenting: a) a comprehensive theoretical analysis of variance reduced zeroth-order (ZO) optimization, b) a novel variance reduced ZO algorithm, called ZO-SVRG, and c) an experimental evaluation of our approach in the context of two compelling applications, black-box chemical material classification and generation of adversarial examples from black-box deep neural network models. Our theoretical analysis uncovers an essential difficulty in the analysis of ZO-SVRG: the unbiased assumption on gradient estimates no longer holds. We prove that compared to its first-order counterpart, ZO-SVRG with a two-point random gradient estimator could suffer an additional error of order $O(1/b)$, where $b$ is the mini-batch size. To mitigate this error, we propose two accelerated versions of ZO-SVRG utilizing
variance reduced gradient estimators, which achieve the best rate known for ZO stochastic optimization (in terms of iterations). Our extensive experimental results show that our approaches outperform other state-of-the-art ZO algorithms, and strike a balance between the convergence rate and the function query complexity.
Author Information
Sijia Liu (MIT-IBM Watson AI Lab, IBM Research AI)
Sijia Liu received the Ph.D. degree in electrical engineering from Syracuse University in 2016. From 2016 to 2017, he was a postdoctoral research fellow in Department of Electrical and Computer Engineering, University of Michigan, Ann Arbor, MI. He is currently a research staff member in IBM Research, MIT-IBM Watson AI Lab. His research interests include machine learning algorithms and statistical signal processing.
Bhavya Kailkhura (Lawrence Livermore National Lab)
Pin-Yu Chen (IBM Research AI)
Paishun Ting (University of Michigan)
Shiyu Chang (IBM T.J. Watson Research Center)
Lisa Amini (IBM Research)
More from the Same Authors
-
2020 : Paper 10: Certified Interpretability Robustness for Class Activation Mapping »
Alex Gu · Tsui-Wei Weng · Pin-Yu Chen · Sijia Liu · Luca Daniel -
2021 Spotlight: PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition »
Cheng-I Jeff Lai · Yang Zhang · Alexander Liu · Shiyu Chang · Yi-Lun Liao · Yung-Sung Chuang · Kaizhi Qian · Sameer Khurana · David Cox · Jim Glass -
2021 : Certified Robustness for Free in Differentially Private Federated Learning »
Chulin Xie · Yunhui Long · Pin-Yu Chen · Krishnaram Kenthapadi · Bo Li -
2021 : MAML is a Noisy Contrastive Learner »
Chia-Hsiang Kao · Wei-Chen Chiu · Pin-Yu Chen -
2021 : QTN-VQC: An End-to-End Learning Framework for Quantum Neural Networks »
Jun Qi · Huck Yang · Pin-Yu Chen -
2021 : Pessimistic Model Selection for Offline Deep Reinforcement Learning »
Huck Yang · Yifan Cui · Pin-Yu Chen -
2022 : Visual Prompting for Adversarial Robustness »
Aochuan Chen · Peter Lorenz · Yuguang Yao · Pin-Yu Chen · Sijia Liu -
2022 : Do Domain Generalization Methods Generalize Well? »
Akshay Mehra · Bhavya Kailkhura · Pin-Yu Chen · Jihun Hamm -
2022 : On the Adversarial Robustness of Vision Transformers »
Rulin Shao · Zhouxing Shi · Jinfeng Yi · Pin-Yu Chen · Cho-Jui Hsieh -
2023 Poster: Neural Image Compression: Generalization, Robustness, and Spectral Biases »
Kelsey Lieberman · James Diffenderfer · Charles Godfrey · Bhavya Kailkhura -
2022 : Panel »
Pin-Yu Chen · Alex Gittens · Bo Li · Celia Cintas · Hilde Kuehne · Payel Das -
2022 : Q & A »
Sayak Paul · Sijia Liu · Pin-Yu Chen -
2022 : Deep dive on foundation models for computer vision »
Pin-Yu Chen -
2022 Tutorial: Foundational Robustness of Foundation Models »
Pin-Yu Chen · Sijia Liu · Sayak Paul -
2022 : Basics in foundation model and robustness »
Pin-Yu Chen · Sijia Liu -
2022 Poster: Models Out of Line: A Fourier Lens on Distribution Shift Robustness »
Sara Fridovich-Keil · Brian Bartoldson · James Diffenderfer · Bhavya Kailkhura · Timo Bremer -
2021 Poster: Predicting Deep Neural Network Generalization with Perturbation Response Curves »
Yair Schiff · Brian Quanz · Payel Das · Pin-Yu Chen -
2021 Poster: Mean-based Best Arm Identification in Stochastic Bandits under Reward Contamination »
Arpan Mukherjee · Ali Tajer · Pin-Yu Chen · Payel Das -
2021 Poster: Understanding Interlocking Dynamics of Cooperative Rationalization »
Mo Yu · Yang Zhang · Shiyu Chang · Tommi Jaakkola -
2021 Poster: Why Lottery Ticket Wins? A Theoretical Perspective of Sample Complexity on Sparse Neural Networks »
Shuai Zhang · Meng Wang · Sijia Liu · Pin-Yu Chen · Jinjun Xiong -
2021 Poster: CAFE: Catastrophic Data Leakage in Vertical Federated Learning »
Xiao Jin · Pin-Yu Chen · Chia-Yi Hsu · Chia-Mu Yu · Tianyi Chen -
2021 Poster: G-PATE: Scalable Differentially Private Data Generator via Private Aggregation of Teacher Discriminators »
Yunhui Long · Boxin Wang · Zhuolin Yang · Bhavya Kailkhura · Aston Zhang · Carl Gunter · Bo Li -
2021 Poster: Adversarial Attack Generation Empowered by Min-Max Optimization »
Jingkang Wang · Tianyun Zhang · Sijia Liu · Pin-Yu Chen · Jiacen Xu · Makan Fardad · Bo Li -
2021 Poster: TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up »
Yifan Jiang · Shiyu Chang · Zhangyang Wang -
2021 : Live Q&A session: MAML is a Noisy Contrastive Learner »
Chia-Hsiang Kao · Wei-Chen Chiu · Pin-Yu Chen -
2021 : Contributed Talk (Oral): MAML is a Noisy Contrastive Learner »
Chia-Hsiang Kao · Wei-Chen Chiu · Pin-Yu Chen -
2021 : SenSE: A Toolkit for Semantic Change Exploration via Word Embedding Alignment »
MaurĂcio Gruppi · Sibel Adali · Pin-Yu Chen -
2021 Poster: A Winning Hand: Compressing Deep Networks Can Improve Out-of-Distribution Robustness »
James Diffenderfer · Brian Bartoldson · Shreya Chaganti · Jize Zhang · Bhavya Kailkhura -
2021 Poster: When does Contrastive Learning Preserve Adversarial Robustness from Pretraining to Finetuning? »
Lijie Fan · Sijia Liu · Pin-Yu Chen · Gaoyuan Zhang · Chuang Gan -
2021 Poster: Formalizing Generalization and Adversarial Robustness of Neural Networks to Weight Perturbations »
Yu-Lin Tsai · Chia-Yi Hsu · Chia-Mu Yu · Pin-Yu Chen -
2021 Poster: PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition »
Cheng-I Jeff Lai · Yang Zhang · Alexander Liu · Shiyu Chang · Yi-Lun Liao · Yung-Sung Chuang · Kaizhi Qian · Sameer Khurana · David Cox · Jim Glass -
2021 Poster: Understanding the Limits of Unsupervised Domain Adaptation via Data Poisoning »
Akshay Mehra · Bhavya Kailkhura · Pin-Yu Chen · Jihun Hamm -
2020 Poster: A Statistical Mechanics Framework for Task-Agnostic Sample Design in Machine Learning »
Bhavya Kailkhura · Jayaraman Thiagarajan · Qunwei Li · Jize Zhang · Yi Zhou · Timo Bremer -
2020 Poster: Automatic Perturbation Analysis for Scalable Certified Robustness and Beyond »
Kaidi Xu · Zhouxing Shi · Huan Zhang · Yihan Wang · Kai-Wei Chang · Minlie Huang · Bhavya Kailkhura · Xue Lin · Cho-Jui Hsieh -
2020 Poster: Training Stronger Baselines for Learning to Optimize »
Tianlong Chen · Weiyi Zhang · Zhou Jingyang · Shiyu Chang · Sijia Liu · Lisa Amini · Zhangyang Wang -
2020 Poster: ScaleCom: Scalable Sparsified Gradient Compression for Communication-Efficient Distributed Training »
Chia-Yu Chen · Jiamin Ni · Songtao Lu · Xiaodong Cui · Pin-Yu Chen · Xiao Sun · Naigang Wang · Swagath Venkataramani · Vijayalakshmi (Viji) Srinivasan · Wei Zhang · Kailash Gopalakrishnan -
2020 Spotlight: Training Stronger Baselines for Learning to Optimize »
Tianlong Chen · Weiyi Zhang · Zhou Jingyang · Shiyu Chang · Sijia Liu · Lisa Amini · Zhangyang Wang -
2020 : Spotlight on women at IBM Research »
Lisa Amini · Francesca Rossi · Celia Cintas · Payel Das -
2020 Poster: Higher-Order Certification For Randomized Smoothing »
Jeet Mohapatra · Ching-Yun Ko · Tsui-Wei Weng · Pin-Yu Chen · Sijia Liu · Luca Daniel -
2020 Poster: Optimizing Mode Connectivity via Neuron Alignment »
Norman J Tatro · Pin-Yu Chen · Payel Das · Igor Melnyk · Prasanna Sattigeri · Rongjie Lai -
2020 Poster: The Lottery Ticket Hypothesis for Pre-trained BERT Networks »
Tianlong Chen · Jonathan Frankle · Shiyu Chang · Sijia Liu · Yang Zhang · Zhangyang Wang · Michael Carbin -
2020 Spotlight: Higher-Order Certification For Randomized Smoothing »
Jeet Mohapatra · Ching-Yun Ko · Tsui-Wei Weng · Pin-Yu Chen · Sijia Liu · Luca Daniel -
2020 Expo Demonstration: Beyond AutoML: AI Automation & Scaling »
Lisa Amini · Nitin Gupta · Parikshit Ram · Kiran Kate · Bhanukiran Vinzamuri · Nathalie Baracaldo · Martin Korytak · Daniel K Weidele · Dakuo Wang -
2019 : Poster Session »
Ahana Ghosh · Javad Shafiee · Akhilan Boopathy · Alex Tamkin · Theodoros Vasiloudis · Vedant Nanda · Ali Baheri · Paul Fieguth · Andrew Bennett · Guanya Shi · Hao Liu · Arushi Jain · Jacob Tyo · Benjie Wang · Boxiao Chen · Carroll Wainwright · Chandramouli Shama Sastry · Chao Tang · Daniel S. Brown · David Inouye · David Venuto · Dhruv Ramani · Dimitrios Diochnos · Divyam Madaan · Dmitrii Krashenikov · Joel Oren · Doyup Lee · Eleanor Quint · elmira amirloo · Matteo Pirotta · Gavin Hartnett · Geoffroy Dubourg-Felonneau · Gokul Swamy · Pin-Yu Chen · Ilija Bogunovic · Jason Carter · Javier Garcia-Barcos · Jeet Mohapatra · Jesse Zhang · Jian Qian · John Martin · Oliver Richter · Federico Zaiter · Tsui-Wei Weng · Karthik Abinav Sankararaman · Kyriakos Polymenakos · Lan Hoang · mahdieh abbasi · Marco Gallieri · Mathieu Seurin · Matteo Papini · Matteo Turchetta · Matthew Sotoudeh · Mehrdad Hosseinzadeh · Nathan Fulton · Masatoshi Uehara · Niranjani Prasad · Oana-Maria Camburu · Patrik Kolaric · Philipp Renz · Prateek Jaiswal · Reazul Hasan Russel · Riashat Islam · Rishabh Agarwal · Alexander Aldrick · Sachin Vernekar · Sahin Lale · Sai Kiran Narayanaswami · Samuel Daulton · Sanjam Garg · Sebastian East · Shun Zhang · Soheil Dsidbari · Justin Goodwin · Victoria Krakovna · Wenhao Luo · Wesley Chung · Yuanyuan Shi · Yuh-Shyang Wang · Hongwei Jin · Ziping Xu -
2019 Poster: Tight Certificates of Adversarial Robustness for Randomly Smoothed Classifiers »
Guang-He Lee · Yang Yuan · Shiyu Chang · Tommi Jaakkola -
2019 Poster: ZO-AdaMM: Zeroth-Order Adaptive Momentum Method for Black-Box Optimization »
Xiangyi Chen · Sijia Liu · Kaidi Xu · Xingguo Li · Xue Lin · Mingyi Hong · David Cox -
2019 Poster: A Game Theoretic Approach to Class-wise Selective Rationalization »
Shiyu Chang · Yang Zhang · Mo Yu · Tommi Jaakkola -
2018 Poster: Efficient Neural Network Robustness Certification with General Activation Functions »
Huan Zhang · Tsui-Wei Weng · Pin-Yu Chen · Cho-Jui Hsieh · Luca Daniel -
2018 Poster: Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives »
Amit Dhurandhar · Pin-Yu Chen · Ronny Luss · Chun-Chen Tu · Paishun Ting · Karthikeyan Shanmugam · Payel Das -
2017 Poster: Dilated Recurrent Neural Networks »
Shiyu Chang · Yang Zhang · Wei Han · Mo Yu · Xiaoxiao Guo · Wei Tan · Xiaodong Cui · Michael Witbrock · Mark Hasegawa-Johnson · Thomas Huang