138 Results

Tutorial
Mon 8:00 Submodular Optimization: From Discrete to Continuous and Back
Hamed Hassani, Amin Karbasi
Poster
Tue 7:00 Min-Max Optimization without Gradients: Convergence and Applications to Black-Box Evasion and Poisoning Attacks
Sijia Liu, Songtao Lu, Xiangyi Chen, Yao Feng, Kaidi Xu, Abdullah Al-Dujaili, Mingyi Hong, Una-May O'Reilly
Poster
Tue 7:00 Towards Understanding the Dynamics of the First-Order Adversaries
Zhun Deng, Hangfeng He, Jiaoyang Huang, Weijie Su
Poster
Tue 7:00 Semismooth Newton Algorithm for Efficient Projections onto $\ell_{1, \infty}$-norm Ball
Dejun Chu, Changshui Zhang, Shiliang Sun, Qing Tao
Poster
Tue 7:00 Quadratically Regularized Subgradient Methods for Weakly Convex Optimization with Weakly Convex Constraints
Runchao Ma, Qihang Lin, Tianbao Yang
Poster
Tue 7:00 Fast Learning of Graph Neural Networks with Guaranteed Generalizability: One-hidden-layer Case
shuai zhang, Meng Wang, Sijia Liu, Pin-Yu Chen, Jinjun Xiong
Poster
Tue 7:00 Searching to Exploit Memorization Effect in Learning with Noisy Labels
QUANMING YAO, Hansi Yang, Bo Han, Gang Niu, James Kwok
Poster
Tue 7:00 Self-Concordant Analysis of Frank-Wolfe Algorithms
Pavel Dvurechenskii, Petr Ostroukhov, Kamil Safin, Shimrit Shtern, Mathias Staudigl
Poster
Tue 7:00 Stochastic Optimization for Non-convex Inf-Projection Problems
Yan Yan, Yi Xu, Lijun Zhang, Wang Xiaoyu, Tianbao Yang
Poster
Tue 7:00 Differentiating through the Fréchet Mean
Aaron Lou, Isay Katsman, Qingxuan Jiang, Serge Belongie, Sernam Lim Lim, Christopher De Sa
Poster
Tue 7:00 What is Local Optimality in Nonconvex-Nonconcave Minimax Optimization?
Chi Jin, Praneeth Netrapalli, Michael Jordan
Poster
Tue 7:00 Uncertainty quantification for nonconvex tensor completion: Confidence intervals, heteroscedasticity and optimality
Changxiao Cai, H. Vincent Poor, Yuxin Chen
Poster
Tue 7:00 Provably Efficient Exploration in Policy Optimization
Qi Cai, Zhuoran Yang, Chi Jin, Zhaoran Wang
Poster
Tue 7:00 Semiparametric Nonlinear Bipartite Graph Representation Learning with Provable Guarantees
Sen Na, Yuwei Luo, Zhuoran Yang, Zhaoran Wang, Mladen Kolar
Poster
Tue 7:00 Accelerated Stochastic Gradient-free and Projection-free Methods
Feihu Huang, Lue Tao, Songcan Chen
Poster
Tue 8:00 Oracle Efficient Private Non-Convex Optimization
Seth Neel, Aaron Roth, Giuseppe Vietri, Steven Wu
Poster
Tue 8:00 Is Local SGD Better than Minibatch SGD?
Blake Woodworth, Kumar Kshitij Patel, Sebastian Stich, Zhen Dai, Brian Bullins, Brendan McMahan, Ohad Shamir, Nati Srebro
Poster
Tue 8:00 Closing the convergence gap of SGD without replacement
Shashank Rajput, Anant Gupta, Dimitris Papailiopoulos
Poster
Tue 8:00 On the Unreasonable Effectiveness of the Greedy Algorithm: Greedy Adapts to Sharpness
Sebastian Pokutta, Mohit Singh, Alfredo Torrico
Poster
Tue 8:00 Stronger and Faster Wasserstein Adversarial Attacks
Kaiwen Wu, Allen Wang, Yaoliang Yu
Poster
Tue 8:00 Distributed Online Optimization over a Heterogeneous Network
Nima Eshraghi, Ben Liang
Poster
Tue 8:00 Finite-Time Convergence in Continuous-Time Optimization
Orlando Romero, mouhacine Benosman
Poster
Tue 8:00 Scalable Identification of Partially Observed Systems with Certainty-Equivalent EM
Kunal Menda, Jean de Becdelievre, Jayesh Gupta, Ilan Kroo, Mykel Kochenderfer, Zachary Manchester
Poster
Tue 9:00 Nearly Linear Row Sampling Algorithm for Quantile Regression
Yi Li, Ruosong Wang, Lin Yang, Hanrui Zhang
Poster
Tue 9:00 Structured Policy Iteration for Linear Quadratic Regulator
Youngsuk Park, Ryan A. Rossi, Zheng Wen, Gang Wu, Handong Zhao
Poster
Tue 10:00 A simpler approach to accelerated optimization: iterative averaging meets optimism
Pooria Joulani, Anant Raj, András György, Csaba Szepesvari
Poster
Tue 10:00 Robust One-Bit Recovery via ReLU Generative Networks: Near-Optimal Statistical Rate and Global Landscape Analysis
Shuang Qiu, Xiaohan Wei, Zhuoran Yang
Poster
Tue 10:00 SCAFFOLD: Stochastic Controlled Averaging for Federated Learning
Praneeth Karimireddy, Satyen Kale, Mehryar Mohri, Sashank Jakkam Reddi, Sebastian Stich, Ananda Theertha Suresh
Poster
Tue 12:00 IPBoost – Non-Convex Boosting via Integer Programming
Marc Pfetsch, Sebastian Pokutta
Poster
Tue 12:00 Stochastic Frank-Wolfe for Constrained Finite-Sum Minimization
GEOFFREY Negiar, Gideon Dresdner, Alicia Yi-Ting Tsai, Laurent El Ghaoui, Francesco Locatello, Robert Freund, Fabian Pedregosa
Poster
Tue 13:00 Optimal Randomized First-Order Methods for Least-Squares Problems
Jonathan Lacotte, Mert Pilanci
Poster
Tue 13:00 StochasticRank: Global Optimization of Scale-Free Discrete Functions
Aleksei Ustimenko, Liudmila Prokhorenkova
Poster
Tue 13:00 Inexact Tensor Methods with Dynamic Accuracies
Nikita Doikov, Yurii Nesterov
Poster
Tue 13:00 Duality in RKHSs with Infinite Dimensional Outputs: Application to Robust Losses
Pierre Laforgue, Alex Lambert, Luc Brogat-Motte, Florence d'Alche-Buc
Poster
Tue 13:00 Online Convex Optimization in the Random Order Model
Dan Garber, Gal Korcia, Kfir Levy
Poster
Tue 13:00 Inertial Block Proximal Methods for Non-Convex Non-Smooth Optimization
Hien Le, Nicolas Gillis, Panagiotis Patrinos
Poster
Tue 14:00 Compressive sensing with un-trained neural networks: Gradient descent finds a smooth approximation
Reinhard Heckel, Mahdi Soltanolkotabi
Poster
Tue 14:00 On the Iteration Complexity of Hypergradient Computation
Riccardo Grazzi, Luca Franceschi, Massimiliano Pontil, Saverio Salzo
Poster
Tue 14:00 Fast Differentiable Sorting and Ranking
Mathieu Blondel, Olivier Teboul, Quentin Berthet, Josip Djolonga
Poster
Tue 14:00 Debiased Sinkhorn barycenters
Hicham Janati, Marco Cuturi, Alexandre Gramfort
Poster
Tue 15:00 When deep denoising meets iterative phase retrieval
Yaotian Wang, Xiaohang Sun, Jason Fleischer
Poster
Tue 18:00 Multi-fidelity Bayesian Optimization with Max-value Entropy Search and its Parallelization
Shion Takeno, Hitoshi Fukuoka, Yuhki Tsukada, Toshiyuki Koyama, Motoki Shiga, Ichiro Takeuchi, Masayuki Karasuyama
Poster
Tue 18:00 Hybrid Stochastic-Deterministic Minibatch Proximal Gradient: Less-Than-Single-Pass Optimization with Nearly Optimal Generalization
Pan Zhou, Xiao-Tong Yuan
Poster
Wed 5:00 Message Passing Least Squares Framework and its Application to Rotation Synchronization
Yunpeng Shi, Gilad Lerman
Poster
Wed 5:00 Optimal Bounds between f-Divergences and Integral Probability Metrics
Rohit Agrawal, Thibaut Horel
Poster
Wed 5:00 Moniqua: Modulo Quantized Communication in Decentralized SGD
Yucheng Lu, Christopher De Sa
Poster
Wed 5:00 Dynamics of Deep Neural Networks and Neural Tangent Hierarchy
Jiaoyang Huang, Horng-Tzer Yau
Poster
Wed 5:00 On the Convergence of Nesterov's Accelerated Gradient Method in Stochastic Settings
Mido Assran, Mike Rabbat
Poster
Wed 5:00 An Accelerated DFO Algorithm for Finite-sum Convex Functions
Yuwen Chen, Antonio Orvieto, Aurelien Lucchi
Poster
Wed 5:00 The Differentiable Cross-Entropy Method
Brandon Amos, Denis Yarats
Poster
Wed 5:00 Don't Waste Your Bits! Squeeze Activations and Gradients for Deep Neural Networks via TinyScript
Fangcheng Fu, Yuzheng Hu, Yihan He, Jiawei Jiang, Yingxia Shao, Ce Zhang, Bin Cui
Poster
Wed 5:00 Optimal approximation for unconstrained non-submodular minimization
Marwa El Halabi, Stefanie Jegelka
Poster
Wed 5:00 Second-Order Provable Defenses against Adversarial Attacks
Sahil Singla, Soheil Feizi
Poster
Wed 5:00 Complexity of Finding Stationary Points of Nonconvex Nonsmooth Functions
Jingzhao Zhang, Hongzhou Lin, Stefanie Jegelka, Suvrit Sra, Ali Jadbabaie
Poster
Wed 5:00 Robust Bayesian Classification Using An Optimistic Score Ratio
Viet Anh Nguyen, Nian Si, Jose Blanchet
Poster
Wed 8:00 Fine-Grained Analysis of Stability and Generalization for Stochastic Gradient Descent
Yunwen Lei, Yiming Ying
Poster
Wed 8:00 Optimizing Black-box Metrics with Adaptive Surrogates
Qijia Jiang, Olaoluwa Adigun, Harikrishna Narasimhan, Mahdi Milani Fard, Maya Gupta
Poster
Wed 8:00 Spectral Graph Matching and Regularized Quadratic Relaxations: Algorithm and Theory
Zhou Fan, Cheng Mao, Yihong Wu, Jiaming Xu
Poster
Wed 8:00 Online mirror descent and dual averaging: keeping pace in the dynamic case
Huang Fang, Nick Harvey, Victor Sanches Portella, Michael Friedlander
Poster
Wed 8:00 Communication-Efficient Distributed PCA by Riemannian Optimization
Long-Kai Huang, Sinno Jialin Pan
Poster
Wed 8:00 On Coresets for Regularized Regression
Rachit Chhaya, Supratim Shit, Anirban Dasgupta
Poster
Wed 9:00 Dual Mirror Descent for Online Allocation Problems
Santiago Balseiro, Haihao Lu, Vahab Mirrokni
Poster
Wed 9:00 Optimization Theory for ReLU Neural Networks Trained with Normalization Layers
Yonatan Dukler, Quanquan Gu, Guido Montufar
Poster
Wed 10:00 Continuous-time Lower Bounds for Gradient-based Algorithms
Michael Muehlebach, Michael Jordan
Poster
Wed 10:00 Efficiently Solving MDPs with Stochastic Mirror Descent
Yujia Jin, Aaron Sidford
Poster
Wed 10:00 Neural Networks are Convex Regularizers: Exact Polynomial-time Convex Optimization Formulations for Two-layer Networks
Mert Pilanci, Tolga Ergen
Poster
Wed 10:00 Quantized Decentralized Stochastic Learning over Directed Graphs
Hossein Taheri, Aryan Mokhtari, Hamed Hassani, Ramtin Pedarsani
Poster
Wed 11:00 Statistically Preconditioned Accelerated Gradient Method for Distributed Optimization
Hadrien Hendrikx, Lin Xiao, Sebastien Bubeck, Francis Bach, Laurent Massoulié
Poster
Wed 11:00 Adaptive Gradient Descent without Descent
Yura Malitsky, Konstantin Mishchenko
Poster
Wed 12:00 Acceleration for Compressed Gradient Descent in Distributed and Federated Optimization
Zhize Li, Dmitry Kovalev, Xun Qian, Peter Richtarik
Poster
Wed 12:00 Curvature-corrected learning dynamics in deep neural networks
Dongsung Huh
Poster
Wed 12:00 A new regret analysis for Adam-type algorithms
Ahmet Alacaoglu, Yura Malitsky, Panayotis Mertikopoulos, Volkan Cevher
Poster
Wed 12:00 Training Linear Neural Networks: Non-Local Convergence and Complexity Results
Armin Eftekhari
Poster
Wed 12:00 On Convergence-Diagnostic based Step Sizes for Stochastic Gradient Descent
Scott Pesme, Aymeric Dieuleveut, Nicolas Flammarion
Poster
Wed 13:00 A Unified Theory of Decentralized SGD with Changing Topology and Local Updates
Anastasia Koloskova, Nicolas Loizou, Sadra Boreiri, Martin Jaggi, Sebastian Stich
Poster
Wed 13:00 Convergence of a Stochastic Gradient Method with Momentum for Non-Smooth Non-Convex Optimization
Vien Mai, Mikael Johansson
Poster
Wed 13:00 Boosting Frank-Wolfe by Chasing Gradients
Cyrille W. Combettes, Sebastian Pokutta
Poster
Wed 13:00 Estimating the Error of Randomized Newton Methods: A Bootstrap Approach
Miles Lopes, Jessie X.T. Chen
Poster
Wed 13:00 Super-efficiency of automatic differentiation for functions defined as a minimum
Pierre Ablin, Gabriel Peyré, Thomas Moreau
Poster
Wed 14:00 Lifted Disjoint Paths with Application in Multiple Object Tracking
Andrea Hornakova, Roberto Henschel, Bodo Rosenhahn, Paul Swoboda
Poster
Wed 14:00 Explicit Gradient Learning for Black-Box Optimization
Elad Sarafian, Mor Sinay, yoram louzoun, Noa Agmon, Sarit Kraus
Poster
Wed 14:00 Variance Reduced Coordinate Descent with Acceleration: New Method With a Surprising Application to Finite-Sum Problems
Filip Hanzely, Dmitry Kovalev, Peter Richtarik
Poster
Wed 15:00 DINO: Distributed Newton-Type Optimization Method
Rixon Crane, Fred Roosta
Poster
Thu 6:00 Sparse Convex Optimization via Adaptively Regularized Hard Thresholding
Kyriakos Axiotis, Maxim Sviridenko
Poster
Thu 6:00 Universal Asymptotic Optimality of Polyak Momentum
Damien Scieur, Fabian Pedregosa
Poster
Thu 6:00 Linear Convergence of Randomized Primal-Dual Coordinate Method for Large-scale Linear Constrained Convex Programming
Daoli Zhu, Lei Zhao
Poster
Thu 6:00 p-Norm Flow Diffusion for Local Graph Clustering
Kimon Fountoulakis, Di Wang, Shenghao Yang
Poster
Thu 6:00 Upper bounds for Model-Free Row-Sparse Principal Component Analysis
Guanyi Wang, Santanu Dey
Poster
Thu 6:00 Input-Sparsity Low Rank Approximation in Schatten Norm
Yi Li, David Woodruff
Poster
Thu 6:00 Stochastic Flows and Geometric Optimization on the Orthogonal Group
Krzysztof Choromanski, David Cheikhi, Jared Quincy Davis, Valerii Likhosherstov, Achille Nazaret, Achraf Bahamou, Xingyou Song, Mrugank Akarte, Jack Parker-Holder, Jacob Bergquist, Yuan Gao, Aldo Pacchiano, Tamas Sarlos, Adrian Weller, Vikas Sindhwani
Poster
Thu 6:00 On Gradient Descent Ascent for Nonconvex-Concave Minimax Problems
Darren Lin, Chi Jin, Michael Jordan
Poster
Thu 6:00 Convex Representation Learning for Generalized Invariance in Semi-Inner-Product Space
Yingyi Ma, Vignesh Ganapathiraman, Yaoliang Yu, Xinhua Zhang
Poster
Thu 6:00 Acceleration through spectral density estimation
Fabian Pedregosa, Damien Scieur
Poster
Thu 6:00 Transparency Promotion with Model-Agnostic Linear Competitors
Hassan Rafique, Tong Wang, Qihang Lin, Arshia Singhani
Poster
Thu 6:00 Stochastic Gauss-Newton Algorithms for Nonconvex Compositional Optimization
Quoc Tran-Dinh, Nate H Pham, Lam Nguyen
Poster
Thu 6:00 Understanding the Impact of Model Incoherence on Convergence of Incremental SGD with Random Reshuffle
Shaocong Ma, Yi Zhou
Poster
Thu 6:00 Stochastic Coordinate Minimization with Progressive Precision for Stochastic Convex Optimization
Sudeep Salgia, Qing Zhao, Sattar Vakili
Poster
Thu 6:00 Performative Prediction
Juan Perdomo, Tijana Zrnic, Celestine Mendler-Dünner, Moritz Hardt
Poster
Thu 6:00 History-Gradient Aided Batch Size Adaptation for Variance Reduced Algorithms
Kaiyi Ji, Zhe Wang, Bowen Weng, Yi Zhou, Wei Zhang, Yingbin LIANG
Poster
Thu 6:00 Interpreting Robust Optimization via Adversarial Influence Functions
Zhun Deng, Cynthia Dwork, Jialiang Wang, Linjun Zhang
Poster
Thu 6:00 A Generic First-Order Algorithmic Framework for Bi-Level Programming Beyond Lower-Level Singleton
Risheng Liu, Pan Mu, Xiaoming Yuan, Shangzhi Zeng, Jin Zhang
Poster
Thu 6:00 Almost Tune-Free Variance Reduction
Bingcong Li, Lingda Wang, Georgios B. Giannakis
Poster
Thu 6:00 Lower Complexity Bounds for Finite-Sum Convex-Concave Minimax Optimization Problems
Guangzeng Xie, Luo Luo, yijiang lian, Zhihua Zhang
Poster
Thu 6:00 Linear Lower Bounds and Conditioning of Differentiable Games
Adam Ibrahim, Waïss Azizian, Gauthier Gidel, Ioannis Mitliagkas
Poster
Thu 7:00 Spectral Frank-Wolfe Algorithm: Strict Complementarity and Linear Convergence
Lijun Ding, Tom Fei, Qiantong Xu, Chengrun Yang
Poster
Thu 7:00 A Nearly-Linear Time Algorithm for Exact Community Recovery in Stochastic Block Model
Peng Wang, Zirui Zhou, Anthony Man-Cho So
Poster
Thu 7:00 On Differentially Private Stochastic Convex Optimization with Heavy-tailed Data
Di Wang, Hanshen Xiao, Srinivas Devadas, Jinhui Xu
Poster
Thu 7:00 Converging to Team-Maxmin Equilibria in Zero-Sum Multiplayer Games
Youzhi Zhang, Bo An
Poster
Thu 7:00 Stochastic Hamiltonian Gradient Methods for Smooth Games
Nicolas Loizou, Hugo Berard, Alexia Jolicoeur-Martineau, Pascal Vincent, Simon Lacoste-Julien, Ioannis Mitliagkas
Poster
Thu 7:00 Momentum Improves Normalized SGD
Ashok Cutkosky, Harsh Mehta
Poster
Thu 8:00 Communication-Efficient Distributed Stochastic AUC Maximization with Deep Neural Networks
Zhishuai Guo, Mingrui Liu, Zhuoning Yuan, Li Shen, Wei Liu, Tianbao Yang
Poster
Thu 8:00 High-dimensional Robust Mean Estimation via Gradient Descent
Yu Cheng, Ilias Diakonikolas, Rong Ge, Mahdi Soltanolkotabi
Poster
Thu 8:00 Coresets for Data-efficient Training of Machine Learning Models
Baharan Mirzasoleiman, Jeff Bilmes, Jure Leskovec
Poster
Thu 8:00 SGD Learns One-Layer Networks in WGANs
Qi Lei, Jason Lee, Alex Dimakis, Constantinos Daskalakis
Poster
Thu 8:00 The Performance Analysis of Generalized Margin Maximizers on Separable Data
Fariborz Salehi, Ehsan Abbasi, Babak Hassibi
Poster
Thu 9:00 Accelerated Message Passing for Entropy-Regularized MAP Inference
Jonathan Lee, Aldo Pacchiano, Peter Bartlett, Michael Jordan
Poster
Thu 9:00 The Implicit Regularization of Stochastic Gradient Flow for Least Squares
Alnur Ali, Edgar Dobriban, Ryan Tibshirani
Poster
Thu 9:00 Improving the Sample and Communication Complexity for Decentralized Non-Convex Optimization: Joint Gradient Estimation and Tracking
Haoran Sun, Songtao Lu, Mingyi Hong
Poster
Thu 12:00 Randomized Block-Diagonal Preconditioning for Parallel Learning
Celestine Mendler-Dünner, Aurelien Lucchi
Poster
Thu 12:00 Random extrapolation for primal-dual coordinate descent
Ahmet Alacaoglu, Olivier Fercoq, Volkan Cevher
Poster
Thu 12:00 Extra-gradient with player sampling for faster convergence in n-player games
Samy Jelassi, Carles Domingo-Enrich, Damien Scieur, Arthur Mensch, Joan Bruna
Poster
Thu 12:00 Conditional gradient methods for stochastically constrained convex minimization
Maria Vladarean, Ahmet Alacaoglu, Ya-Ping Hsieh, Volkan Cevher
Poster
Thu 12:00 The Complexity of Finding Stationary Points with Stochastic Gradient Descent
Yoel Drori, Ohad Shamir
Poster
Thu 13:00 Stochastic Subspace Cubic Newton Method
Filip Hanzely, Nikita Doikov, Yurii Nesterov, Peter Richtarik
Poster
Thu 13:00 Efficient Proximal Mapping of the 1-path-norm of Shallow Networks
Fabian Latorre, Paul Rolland, Shaul Nadav Hallak, Volkan Cevher
Poster
Thu 13:00 Topic Modeling via Full Dependence Mixtures
Dan Fisher, Mark Kozdoba, Shie Mannor
Poster
Thu 14:00 Regularized Optimal Transport is Ground Cost Adversarial
François-Pierre Paty, Marco Cuturi
Poster
Thu 14:00 Anderson Acceleration of Proximal Gradient Methods
Vien Mai, Mikael Johansson
Poster
Thu 14:00 From Sets to Multisets: Provable Variational Inference for Probabilistic Integer Submodular Models
Aytunc Sahin, Yatao Bian, Joachim Buhmann, Andreas Krause
Poster
Thu 15:00 Stochastic Optimization for Regularized Wasserstein Estimators
Marin Ballu, Quentin Berthet, Francis Bach
Poster
Thu 17:00 Multi-objective Bayesian Optimization using Pareto-frontier Entropy
Shinya Suzuki, Shion Takeno, Tomoyuki Tamura, Kazuki Shitara, Masayuki Karasuyama
Poster
Thu 17:00 Projection-free Distributed Online Convex Optimization with $O(\sqrt{T})$ Communication Complexity
Yuanyu Wan, Wei-Wei Tu, Lijun Zhang
Workshop
Fri 9:10 Talk by Francis Bach - Second Order Strikes Back - Globally convergent Newton methods for ill-conditioned generalized self-concordant Losses
Francis Bach
Workshop
Fri 12:05 Short Talk 4 - Adaptive Regret for Online Control
Edgar Minasyan
Workshop
Fri 12:35 Short Talk 6 - Preference learning along multiple criteria: A game-theoretic perspective
Kush Bhatia
Workshop
Sat 9:00 Optimal Query Complexity of Secure Stochastic Convex Optimization by Wei Tang
Workshop
Sat 9:30 Efficient Privacy-Preserving Stochastic Nonconvex Optimization by Lingxiao Wang
Workshop
Sat 14:00 Keynote Session 5: Advances and Open Problems in Federated Learning, by Brendan McMahan (Google)
Brendan McMahan