Timezone: »
Several works have aimed to explain why overparameterized neural networks generalize well when trained by Stochastic Gradient Descent (SGD). The consensus explanation that has emerged credits the randomized nature of SGD for the bias of the training process towards low-complexity models and, thus, for implicit regularization. We take a careful look at this explanation in the context of image classification with common deep neural network architectures. We find that if we do not regularize \emph{explicitly}, then SGD can be easily made to converge to poorly-generalizing, high-complexity models: all it takes is to first train on a random labeling on the data, before switching to properly training with the correct labels. In contrast, we find that in the presence of explicit regularization, pretraining with random labels has no detrimental effect on SGD. We believe that our results give evidence that explicit regularization plays a far more important role in the success of overparameterized neural networks than what has been understood until now. Specifically, in suppressing complicated models that got lucky with the training data, regularization not only makes simple models that fit the data well the global optima, but it also clears the way to make them discoverable by local methods, such as SGD.
Author Information
Shengchao Liu (MILA-UdeM)
Dimitris Papailiopoulos (University of Wisconsin-Madison)
Dimitris Achlioptas (University of Athens)
More from the Same Authors
-
2021 : Multi-task Learning with Domain Knowledge for Molecular Property Prediction »
Shengchao Liu · Meng Qu · Zuobai Zhang · Jian Tang -
2022 : Active Learning is a Strong Baseline for Data Subset Selection »
Dongmin Park · Dimitris Papailiopoulos · Kangwook Lee -
2022 : A Better Way to Decay: Proximal Gradient Training Algorithms for Neural Nets »
Liu Yang · Jifan Zhang · Joseph Shenouda · Dimitris Papailiopoulos · Kangwook Lee · Robert Nowak -
2022 : MoleculeCLIP: Learning Transferable Molecule Multi-Modality Models via Natural Language »
Shengchao Liu · Weili Nie · Chengpeng Wang · Jiarui Lu · Zhuoran Qiao · Ling Liu · Jian Tang · Anima Anandkumar · Chaowei Xiao -
2022 : ChemSpacE: Interpretable and Interactive Chemical Space Exploration »
Yuanqi Du · Xian Liu · Nilay Shah · Shengchao Liu · Jieyu Zhang · Bolei Zhou -
2022 : Relational Out-of-Distribution Generalization »
Xinyu Yang · Xinyi Pan · Shengchao Liu · Huaxiu Yao -
2022 : GraphCG: Unsupervised Discovery of Steerable Factors in Graphs »
Shengchao Liu · Chengpeng Wang · Weili Nie · Hanchen Wang · Jiarui Lu · Bolei Zhou · Jian Tang -
2023 Poster: Dissecting Chain-of-Thought: A Study on Compositional In-Context Learning of MLPs »
Yingcong Li · Kartik Sreenivasan · Angeliki Giannou · Dimitris Papailiopoulos · Samet Oymak -
2023 Workshop: AI for Science: from Theory to Practice »
Yuanqi Du · Max Welling · Yoshua Bengio · Marinka Zitnik · Carla Gomes · Jure Leskovec · Maria Brbic · Wenhao Gao · Kexin Huang · Ziming Liu · Rocío Mercado · Miles Cranmer · Shengchao Liu · Lijing Wang -
2022 Poster: LIFT: Language-Interfaced Fine-Tuning for Non-language Machine Learning Tasks »
Tuan Dinh · Yuchen Zeng · Ruisu Zhang · Ziqian Lin · Michael Gira · Shashank Rajput · Jy-yong Sohn · Dimitris Papailiopoulos · Kangwook Lee -
2022 Poster: Rare Gems: Finding Lottery Tickets at Initialization »
Kartik Sreenivasan · Jy-yong Sohn · Liu Yang · Matthew Grinde · Alliot Nagle · Hongyi Wang · Eric Xing · Kangwook Lee · Dimitris Papailiopoulos -
2021 Workshop: AI for Science: Mind the Gaps »
Payal Chandak · Yuanqi Du · Tianfan Fu · Wenhao Gao · Kexin Huang · Shengchao Liu · Ziming Liu · Gabriel Spadon · Max Tegmark · Hanchen Wang · Adrian Weller · Max Welling · Marinka Zitnik -
2021 Poster: An Exponential Improvement on the Memorization Capacity of Deep Threshold Networks »
Shashank Rajput · Kartik Sreenivasan · Dimitris Papailiopoulos · Amin Karbasi -
2020 Poster: Attack of the Tails: Yes, You Really Can Backdoor Federated Learning »
Hongyi Wang · Kartik Sreenivasan · Shashank Rajput · Harit Vishwakarma · Saurabh Agarwal · Jy-yong Sohn · Kangwook Lee · Dimitris Papailiopoulos -
2020 Poster: Optimal Lottery Tickets via Subset Sum: Logarithmic Over-Parameterization is Sufficient »
Ankit Pensia · Shashank Rajput · Alliot Nagle · Harit Vishwakarma · Dimitris Papailiopoulos -
2020 Spotlight: Optimal Lottery Tickets via Subset Sum: Logarithmic Over-Parameterization is Sufficient »
Ankit Pensia · Shashank Rajput · Alliot Nagle · Harit Vishwakarma · Dimitris Papailiopoulos -
2019 Poster: N-Gram Graph: Simple Unsupervised Representation for Graphs, with Applications to Molecules »
Shengchao Liu · Mehmet Demirel · Yingyu Liang -
2019 Spotlight: N-Gram Graph: Simple Unsupervised Representation for Graphs, with Applications to Molecules »
Shengchao Liu · Mehmet Demirel · Yingyu Liang -
2019 Poster: DETOX: A Redundancy-based Framework for Faster and More Robust Gradient Aggregation »
Shashank Rajput · Hongyi Wang · Zachary Charles · Dimitris Papailiopoulos -
2018 : Contributed Work »
Thaer Moustafa Dieb · Aditya Balu · Amir H. Khasahmadi · Viraj Shah · Boris Knyazev · Payel Das · Garrett Goh · Georgy Derevyanko · Gianni De Fabritiis · Reiko Hagawa · John Ingraham · David Belanger · Jialin Song · Kim Nicoli · Miha Skalic · Michelle Wu · Niklas Gebauer · Peter Bjørn Jørgensen · Ryan-Rhys Griffiths · Shengchao Liu · Sheshera Mysore · Hai Leong Chieu · Philippe Schwaller · Bart Olsthoorn · Bianca-Cristina Cristescu · Wei-Cheng Tseng · Seongok Ryu · Iddo Drori · Kevin Yang · Soumya Sanyal · Zois Boukouvalas · Rishi Bedi · Arindam Paul · Sambuddha Ghosal · Daniil Bash · Clyde Fare · Zekun Ren · Ali Oskooei · Minn Xuan Wong · Paul Sinz · Théophile Gaudin · Wengong Jin · Paul Leu -
2018 Poster: The Effect of Network Width on the Performance of Large-batch Training »
Lingjiao Chen · Hongyi Wang · Jinman Zhao · Dimitris Papailiopoulos · Paraschos Koutris -
2018 Poster: ATOMO: Communication-efficient Learning via Atomic Sparsification »
Hongyi Wang · Scott Sievert · Shengchao Liu · Zachary Charles · Dimitris Papailiopoulos · Stephen Wright -
2016 Poster: Cyclades: Conflict-free Asynchronous Machine Learning »
Xinghao Pan · Maximilian Lam · Stephen Tu · Dimitris Papailiopoulos · Ce Zhang · Michael Jordan · Kannan Ramchandran · Christopher Ré · Benjamin Recht -
2015 Poster: Orthogonal NMF through Subspace Exploration »
Megasthenis Asteris · Dimitris Papailiopoulos · Alex Dimakis -
2015 Poster: Sparse PCA via Bipartite Matchings »
Megasthenis Asteris · Dimitris Papailiopoulos · Anastasios Kyrillidis · Alex Dimakis -
2015 Poster: Parallel Correlation Clustering on Big Graphs »
Xinghao Pan · Dimitris Papailiopoulos · Samet Oymak · Benjamin Recht · Kannan Ramchandran · Michael Jordan