Filter by Keyword:

72 Results

Spotlight
Tue 5:20 Stochastic Sign Descent Methods: New Algorithms and Better Theory
Mher Safaryan, Peter Richtarik
Spotlight
Tue 5:20 Offline Contextual Bandits with Overparameterized Models
David Brandfonbrener, Will Whitney, Rajesh Ranganath, Joan Bruna
Spotlight
Tue 5:30 A Hybrid Variance-Reduced Method for Decentralized Stochastic Non-Convex Optimization
Ran Xin, Usman Khan, Soummya Kar
Spotlight
Tue 5:35 Zeroth-Order Non-Convex Learning via Hierarchical Dual Averaging
Amélie Héliou, Matthieu Martin, Panayotis Mertikopoulos, Thibaud J Rahier
Spotlight
Tue 7:25 Variational Data Assimilation with a Learned Inverse Observation Operator
Thomas Frerix, Dmitrii Kochkov, Jamie Smith, Daniel Cremers, Michael Brenner, Stephan Hoyer
Poster
Tue 9:00 A Hybrid Variance-Reduced Method for Decentralized Stochastic Non-Convex Optimization
Ran Xin, Usman Khan, Soummya Kar
Poster
Tue 9:00 Decentralized Riemannian Gradient Descent on the Stiefel Manifold
Shixiang Chen, Alfredo Garcia, Mingyi Hong, Shahin Shahrampour
Poster
Tue 9:00 Zeroth-Order Non-Convex Learning via Hierarchical Dual Averaging
Amélie Héliou, Matthieu Martin, Panayotis Mertikopoulos, Thibaud J Rahier
Poster
Tue 9:00 Offline Contextual Bandits with Overparameterized Models
David Brandfonbrener, Will Whitney, Rajesh Ranganath, Joan Bruna
Poster
Tue 9:00 Variational Data Assimilation with a Learned Inverse Observation Operator
Thomas Frerix, Dmitrii Kochkov, Jamie Smith, Daniel Cremers, Michael Brenner, Stephan Hoyer
Poster
Tue 9:00 Stochastic Sign Descent Methods: New Algorithms and Better Theory
Mher Safaryan, Peter Richtarik
Spotlight
Tue 17:30 Joining datasets via data augmentation in the label space for neural networks
Jake Zhao Zhao, Mingfeng Ou, linji Xue, Yunkai Cui, Sai Wu, Gang Chen
Spotlight
Tue 17:45 Training Quantized Neural Networks to Global Optimality via Semidefinite Programming
Burak Bartan, Mert Pilanci
Spotlight
Tue 19:40 Neural Pharmacodynamic State Space Modeling
Zeshan Hussain, Rahul G. Krishnan, David Sontag
Spotlight
Tue 19:45 Three Operator Splitting with a Nonconvex Loss Function
Alp Yurtsever, Varun Mangalick, Suvrit Sra
Spotlight
Tue 19:45 On a Combination of Alternating Minimization and Nesterov's Momentum
Sergey Guminov, Pavel Dvurechenskii, Nazarii Tupitsa, Alexander Gasnikov
Poster
Tue 21:00 On a Combination of Alternating Minimization and Nesterov's Momentum
Sergey Guminov, Pavel Dvurechenskii, Nazarii Tupitsa, Alexander Gasnikov
Poster
Tue 21:00 Joining datasets via data augmentation in the label space for neural networks
Jake Zhao Zhao, Mingfeng Ou, linji Xue, Yunkai Cui, Sai Wu, Gang Chen
Poster
Tue 21:00 Three Operator Splitting with a Nonconvex Loss Function
Alp Yurtsever, Varun Mangalick, Suvrit Sra
Poster
Tue 21:00 Training Quantized Neural Networks to Global Optimality via Semidefinite Programming
Burak Bartan, Mert Pilanci
Oral
Wed 5:00 Optimizing persistent homology based functions
Mathieu Carrière, Frederic Chazal, Marc Glisse, Yuichi Ike, Hariprasad Kannan, Yuhei Umeda
Spotlight
Wed 5:20 Debiasing a First-order Heuristic for Approximate Bi-level Optimization
Valerii Likhosherstov, Xingyou Song, Krzysztof Choromanski, Jared Quincy Davis, Adrian Weller
Spotlight
Wed 5:25 SMG: A Shuffling Gradient-Based Method with Momentum
Trang Tran, Lam Nguyen, Quoc Tran-Dinh
Spotlight
Wed 5:30 Regret Minimization in Stochastic Non-Convex Learning via a Proximal-Gradient Approach
Nadav Hallak, Panayotis Mertikopoulos, Volkan Cevher
Spotlight
Wed 5:35 MARINA: Faster Non-Convex Distributed Learning with Compression
Eduard Gorbunov, Konstantin Burlachenko, Zhize Li, Peter Richtarik
Spotlight
Wed 5:40 Bilevel Optimization: Convergence Analysis and Enhanced Design
Kaiyi Ji, Junjie Yang, Yingbin LIANG
Spotlight
Wed 5:45 Learning from History for Byzantine Robust Optimization
Praneeth Karimireddy, Lie He, Martin Jaggi
Spotlight
Wed 6:25 A Modular Analysis of Provable Acceleration via Polyak's Momentum: Training a Wide ReLU Network and a Deep Linear Network
Jun-Kun Wang, Chi-Heng Lin, Jake Abernethy
Spotlight
Wed 6:35 Fast Algorithms for Stackelberg Prediction Game with Least Squares Loss
jiali wang, He Chen, Rujun Jiang, Xudong Li, Zihao Li
Spotlight
Wed 6:40 TempoRL: Learning When to Act
André Biedenkapp, Raghu Rajan, Frank Hutter, Marius Lindauer
Poster
Wed 9:00 A Modular Analysis of Provable Acceleration via Polyak's Momentum: Training a Wide ReLU Network and a Deep Linear Network
Jun-Kun Wang, Chi-Heng Lin, Jake Abernethy
Poster
Wed 9:00 Learning from History for Byzantine Robust Optimization
Praneeth Karimireddy, Lie He, Martin Jaggi
Poster
Wed 9:00 Regret Minimization in Stochastic Non-Convex Learning via a Proximal-Gradient Approach
Nadav Hallak, Panayotis Mertikopoulos, Volkan Cevher
Poster
Wed 9:00 Optimizing persistent homology based functions
Mathieu Carrière, Frederic Chazal, Marc Glisse, Yuichi Ike, Hariprasad Kannan, Yuhei Umeda
Poster
Wed 9:00 MARINA: Faster Non-Convex Distributed Learning with Compression
Eduard Gorbunov, Konstantin Burlachenko, Zhize Li, Peter Richtarik
Poster
Wed 9:00 Bilevel Optimization: Convergence Analysis and Enhanced Design
Kaiyi Ji, Junjie Yang, Yingbin LIANG
Poster
Wed 9:00 Fast Algorithms for Stackelberg Prediction Game with Least Squares Loss
jiali wang, He Chen, Rujun Jiang, Xudong Li, Zihao Li
Poster
Wed 9:00 SMG: A Shuffling Gradient-Based Method with Momentum
Trang Tran, Lam Nguyen, Quoc Tran-Dinh
Poster
Wed 9:00 TempoRL: Learning When to Act
André Biedenkapp, Raghu Rajan, Frank Hutter, Marius Lindauer
Poster
Wed 9:00 Debiasing a First-order Heuristic for Approximate Bi-level Optimization
Valerii Likhosherstov, Xingyou Song, Krzysztof Choromanski, Jared Quincy Davis, Adrian Weller
Spotlight
Wed 17:35 Leveraging Non-uniformity in First-order Non-convex Optimization
Jincheng Mei, Yue Gao, Bo Dai, Csaba Szepesvari, Dale Schuurmans
Spotlight
Wed 17:35 Improved Corruption Robust Algorithms for Episodic Reinforcement Learning
Yifang Chen, Simon Du, Kevin Jamieson
Poster
Wed 21:00 Leveraging Non-uniformity in First-order Non-convex Optimization
Jincheng Mei, Yue Gao, Bo Dai, Csaba Szepesvari, Dale Schuurmans
Poster
Wed 21:00 Improved Corruption Robust Algorithms for Episodic Reinforcement Learning
Yifang Chen, Simon Du, Kevin Jamieson
Spotlight
Thu 5:30 Learning disentangled representations via product manifold projection
Marco Fumero, Luca Cosmo, Simone Melzi, Emanuele Rodola
Spotlight
Thu 5:45 A Scalable Second Order Method for Ill-Conditioned Matrix Completion from Few Samples
Christian Kümmerle, Claudio Mayrink Verdun
Oral
Thu 6:00 Dash: Semi-Supervised Learning with Dynamic Thresholding
Yi Xu, Lei Shang, Jinxing Ye, Qi Qian, Yufeng Li, Baigui Sun, Hao Li, rong jin
Spotlight
Thu 6:30 Phase Transitions, Distance Functions, and Implicit Neural Representations
Yaron Lipman
Spotlight
Thu 6:35 Quantum algorithms for reinforcement learning with a generative model
Daochen Wang, Aarthi Sundaram, Robin Kothari, Ashish Kapoor, Martin Roetteler
Poster
Thu 9:00 Learning disentangled representations via product manifold projection
Marco Fumero, Luca Cosmo, Simone Melzi, Emanuele Rodola
Poster
Thu 9:00 A Scalable Second Order Method for Ill-Conditioned Matrix Completion from Few Samples
Christian Kümmerle, Claudio Mayrink Verdun
Poster
Thu 9:00 Quantum algorithms for reinforcement learning with a generative model
Daochen Wang, Aarthi Sundaram, Robin Kothari, Ashish Kapoor, Martin Roetteler
Poster
Thu 9:00 Phase Transitions, Distance Functions, and Implicit Neural Representations
Yaron Lipman
Poster
Thu 9:00 Dash: Semi-Supervised Learning with Dynamic Thresholding
Yi Xu, Lei Shang, Jinxing Ye, Qi Qian, Yufeng Li, Baigui Sun, Hao Li, rong jin
Spotlight
Thu 18:40 Optimal Non-Convex Exact Recovery in Stochastic Block Model via Projected Power Method
Peng Wang, Huikang Liu, Zirui Zhou, Anthony Man-Cho So
Spotlight
Thu 20:30 Decentralized Riemannian Gradient Descent on the Stiefel Manifold
Shixiang Chen, Alfredo Garcia, Mingyi Hong, Shahin Shahrampour
Spotlight
Thu 20:40 A Second look at Exponential and Cosine Step Sizes: Simplicity, Adaptivity, and Performance
Xiaoyu Li, Zhenxun Zhuang, Francesco Orabona
Spotlight
Thu 20:45 A Value-Function-based Interior-point Method for Non-convex Bi-level Optimization
Risheng Liu, Xuan Liu, Xiaoming Yuan, Shangzhi Zeng, Jin Zhang
Poster
Thu 21:00 A Value-Function-based Interior-point Method for Non-convex Bi-level Optimization
Risheng Liu, Xuan Liu, Xiaoming Yuan, Shangzhi Zeng, Jin Zhang
Poster
Thu 21:00 A Second look at Exponential and Cosine Step Sizes: Simplicity, Adaptivity, and Performance
Xiaoyu Li, Zhenxun Zhuang, Francesco Orabona
Poster
Thu 21:00 Optimal Non-Convex Exact Recovery in Stochastic Block Model via Projected Power Method
Peng Wang, Huikang Liu, Zirui Zhou, Anthony Man-Cho So
Poster
Thu 21:00 Neural Pharmacodynamic State Space Modeling
Zeshan Hussain, Rahul G. Krishnan, David Sontag
Workshop
Sat 13:02 Sparse Bayesian Learning via Stepwise Regression
Sebastian Ament, Carla Gomes
Workshop
On Frank-Wolfe Adversarial Training
Theodoros Tsiligkaridis, Jay Roberts
Workshop
Algorithmic Recourse in Partially and Fully Confounded Settings Through Bounding Counterfactual Effects
Julius von Kügelgen, Nikita Agarwal, Jakob Zeitler, Afsaneh Mastouri, Bernhard Schölkopf
Workshop
On Low Rank Training of Deep Neural Networks
Sid Kamalakara, Acyr Locatelli, Bharat Venkitesh, Jimmy Ba, Yarin Gal, Aidan Gomez
Workshop
Benchmarking Differential Privacy and Federated Learning for BERT Models
Priyam Basu, Rakshit Naidu, Zumrut Muftuoglu, Sahib Singh, FatemehSadat Mireshghallah
Workshop
Unsupervised Information Obfuscation for Split Inference of Neural Networks
Mohammad Samragh, Hossein Hosseini, Aleksei Triastcyn, Kambiz Azarian, Joseph B Soriaga, Farinaz Koushanfar
Workshop
Sparse Bayesian Learning via Stepwise Regression
Sebastian Ament, Carla Gomes
Workshop
A general sample complexity analysis of vanilla policy gradient
Rui Yuan, Robert Gower, Alessandro Lazaric