Monday June 24
Opening reception 5:30-7:30pm, 103AB
Tuesday June 25
Continental Breakfast (8:15 AM -- 9:00AM)
Session 1 (STOC Sister Session)
8:50 AMOpening remarks
9:00 AMJerry Li, Aleksandar Nikolov, Ilya Razenshteyn, Erik Waingarten
On Mean Estimation for General Norms with Statistical Queries
9:10 AMSamuel B. Hopkins, Jerry Li
How Hard is Robust Mean Estimation?
9:20 AMYeshwanth Cherapanamjeri, Nicolas Flammarion, Peter Bartlett
Fast Mean Estimation with Sub-Gaussian Rates
9:30 AMDaniel Alabi, Adam Tauman Kalai, Katrina Ligett, Cameron Musco, Christos Tzamos, Ellen Vitercik
Learning to Prune: Speeding up Repeated Computations
9:40 AMMichal Derezinski
Fast determinantal point processes via distortion-free intermediate sampling
9:50 AMYair Carmon, John C. Duchi, Aaron Sidford, Kevin Tian
A Rank-1 Sketch for Matrix Multiplicative Weights
10:00 AMZohar Karnin, Edo Liberty
Discrepancy, Coresets, and Sketches in Machine Learning
10:10 AMMatthew Brennan, Guy Bresler
Optimal Average-Case Reductions to Sparse PCA: From Weak Assumptions to Strong Hardness
10:20 AMMatthew Brennan, Guy Bresler, Wasim Huleihel
Universality of Computational Lower Bounds for Submatrix Detection
10:30 AMJan Hązła, Ali Jadbabaie, Elchanan Mossel, M. Amin Rahimian
Reasoning in Bayesian Opinion Exchange Networks Is PSPACE-Hard
10:40 AMDylan Foster, Andrej Risteski
Sum-of-squares meets square loss: Fast rates for agnostic tensor completion
10:50 AMSamuel B. Hopkins, Tselil Schramm, Jonathan Shi
A Robust Spectral Algorithm for Overcomplete Tensor Decomposition
Coffee Break (11:00 AM) / FCRC Keynote (11:20 AM) / Lunch (12:30 PM)
Session 2 (Online Learning)
2:00 PMDan Garber
On the Regret Minimization of Nonconvex Online Gradient Ascent for Online PCA
2:10 PMNaman Agarwal, Alon Gonen, Elad Hazan
Learning in Non-convex Games with an Optimization Oracle
2:20 PMAshok Cutkosky
Combining Online Learning Guarantees
2:30 PMAshok Cutkosky
Artificial Constraints and Hints for Unbounded Online Learning
2:40 PMZakaria Mhammedi, Wouter M. Koolen, Tim van Erven
Lipschitz Adaptivity with Multiple Learning Rates in Online Learning
2:50 PMChristian Coester, James R. Lee
Pure Entropic Regularization for MTS
3:00 PMYun Kuen Cheung, Georgios Piliouras
Vortices Instead of Equilibria in MinMax Optimization: Chaos and Butterfly Effects of Online Learning in Zero-Sum Games
3:10 PMMingda Qiao, Gregory Valiant
A Theory of Selective Prediction
3:20 PMVaggos Chatziafratis, Tim Roughgarden, Joshua R. Wang
On the Computational Power of Online Gradient Descent
Afternoon Break (3:30 PM)
Session 3 (Testing and Distribution Learning)
4:00 PMDamian Straszak, Nisheeth K. Vishnoi
Maximum Entropy Distributions: Bit Complexity and Stability
4:10 PMJonathan Weed, Quentin Berthet
Estimation of smooth densities in Wasserstein distance
4:20 PMOlivier Bousquet, Daniel Kane, Shay Moran
The Optimal Approximation Factor in Density Estimation
4:30 PMIlias Diakonikolas, Themis Gouleakis, Daniel M. Kane, Sankeerth Rao
Communication and Memory Efficient Testing of Discrete Distributions
4:40 PMJayadev Acharya, Clément L. Canonne, Himanshu Tyagi
Inference under Local Constraints: Lower Bounds from Chi-Square Contractions
4:50 PMMaryam Aliakbarpour, Themis Gouleakis, John Peebles, Ronitt Rubinfeld, Anak Yodpinyanee
Towards Testing Monotonicity of Distributions Over General Posets
5:00 PMMaryam Aliakbarpour, Ravi Kumar, Ronitt Rubinfeld
Testing Mixtures of Discrete Distributions
5:10 PMIlias Diakonikolas, Daniel M. Kane, John Peebles
Testing Identity of Multidimensional Histograms
5:20 PMMeimei Liu, Zuofeng Shang, Guang Cheng
Sharp Theoretical Analysis for Nonparametric Testing under Random Projection
5:30 PMIvona Bezakova, Antonio Blanca, Zongchen Chen, Daniel Stefankovic, Eric Vigoda
Lower bounds for testing graphical models: colorings and antiferromagnetic Ising models
5:40 PMYeshwanth Cherapanamjeri, Peter Bartlett
Testing Markov Chains Without Hitting
5:50 PMAnindya De, Elchanan Mossel, Joe Neeman
Is your function low dimensional?
Word from Our Sponsors
6:00 PMSponsors' talks
Poster Session 1
6:00 PMPoster session 1
  1. On Mean Estimation for General Norms with Statistical Queries
  2. How Hard is Robust Mean Estimation?
  3. Fast Mean Estimation with Sub-Gaussian Rates
  4. Learning to Prune: Speeding up Repeated Computations
  5. Fast determinantal point processes via distortion-free intermediate sampling
  6. A Rank-1 Sketch for Matrix Multiplicative Weights
  7. Discrepancy, Coresets, and Sketches in Machine Learning
  8. Optimal Average-Case Reductions to Sparse PCA: From Weak Assumptions to Strong Hardness
  9. Universality of Computational Lower Bounds for Submatrix Detection
  10. Reasoning in Bayesian Opinion Exchange Networks Is PSPACE-Hard
  11. Sum-of-squares meets square loss: Fast rates for agnostic tensor completion
  12. A Robust Spectral Algorithm for Overcomplete Tensor Decomposition
  13. On the Regret Minimization of Nonconvex Online Gradient Ascent for Online PCA
  14. Learning in Non-convex Games with an Optimization Oracle
  15. Combining Online Learning Guarantees
  16. Artificial Constraints and Hints for Unbounded Online Learning
  17. Lipschitz Adaptivity with Multiple Learning Rates in Online Learning
  18. Pure Entropic Regularization for MTS
  19. Vortices Instead of Equilibria in MinMax Optimization: Chaos and Butterfly Effects of Online Learning in Zero-Sum Games
  20. A Theory of Selective Prediction
  21. On the Computational Power of Online Gradient Descent
  22. Maximum Entropy Distributions: Bit Complexity and Stability
  23. Estimation of smooth densities in Wasserstein distance
  24. The Optimal Approximation Factor in Density Estimation
  25. Communication and Memory Efficient Testing of Discrete Distributions
  26. Inference under Local Constraints: Lower Bounds from Chi-Square Contractions
  27. Towards Testing Monotonicity of Distributions Over General Posets
  28. Testing Mixtures of Discrete Distributions
  29. Testing Identity of Multidimensional Histograms
  30. Sharp Theoretical Analysis for Nonparametric Testing under Random Projection
  31. Lower bounds for testing graphical models: colorings and antiferromagnetic Ising models
  32. Testing Markov Chains Without Hitting
  33. Is your function low dimensional?
  34. The Gap Between Model-Based and Model-Free Methods on the Linear Quadratic Regulator: An Asymptotic Viewpoint
  35. Finite-Time Error Bounds For Linear Stochastic Approximation and TD Learning
  36. Model-based RL in Contextual Decision Processes: PAC bounds and Exponential Improvements over Model-free Approaches
  37. Non-asymptotic Analysis of Biased Stochastic Approximation Scheme
  38. Learning Linear Dynamical Systems with Semi-Parametric Least Squares
Wednesday June 26
Continental Breakfast (8:15 AM -- 9:00AM)
Session 4 (Inference and Estimation)
9:00 AMLaurent Massoulié, Ludovic Stephan, Don Towsley
Planting trees in graphs, and finding them back
9:10 AMSami Davies, Miklos Racz, Cyrus Rashtchian
Reconstructing Trees from Traces
9:20 AMLudovic Stephan, Laurent Massoulié
Robustness of spectral methods for community detection
9:30 AMYingjie Fei, Yudong Chen
Achieving the Bayes Error Rate in Stochastic Block Model by SDP, Robustly
9:40 AMRobert Busa-Fekete, Dimitris Fotakis, Balazs Szorenyi, Manolis Zampetakis
Optimal Learning for Mallows Block Model
9:50 AMVishesh Jain, Frederic Koehler, Jingbo Liu, Elchanan Mossel
Accuracy-Memory Tradeoffs and Phase Transitions in Belief Propagation
10:00 AMSurbhi Goel, Daniel M. Kane, Adam R. Klivans
Learning Ising Models with Independent Failures
10:10 AMVictor-Emmanuel Brunel
Learning rates for Gaussian mixtures under group invariance
10:20 AMJeongyeol Kwon, Wei Qian, Constantine Caramanis, Yudong Chen, Damek Davis
Global Convergence of the EM Algorithm for Mixtures of Two Component Linear Regression
10:30 AMArun Sai Suggala, Kush Bhatia, Pradeep Ravikumar, Prateek Jain
Adaptive Hard Thresholding for Near-optimal Consistent Robust Regression
10:40 AMConstantinos Daskalakis, Themis Gouleakis, Christos Tzamos, Emmanouil Zampetakis
Computationally and Statistically Efficient Truncated Regression
10:50 AMGalen Reeves, Jiaming Xu, Ilias Zadik
The All-or-Nothing Phenomenon in Sparse Linear Regression
Coffee Break (11:00 AM) / FCRC Keynote (11:20 AM) / WiML Lunch (12:30)/ Lunch (12:30 PM)
Afternoon Break (3:30 PM)
Session 6 (Bandits)
4:00 PMTor Lattimore, Csaba Szepesvari
An Information-Theoretic Approach to Minimax Regret in Partial Monitoring
4:10 PMSandeep Juneja, Subhashini Krishnasamy
Sample complexity of partition identification using multi-armed bandits
4:20 PMNadav Merlis, Shie Mannor
Batch-Size Independent Regret Bounds for the Combinatorial Multi-Armed Bandit Problem
4:30 PMMark Braverman, Jieming Mao, Jon Schneider, S. Matthew Weinberg
Multi-armed Bandit Problems with Strategic Arms
4:40 PMAnupam Gupta, Tomer Koren, Kunal Talwar
Better Algorithms for Stochastic Bandits with Adversarial Corruptions
4:50 PMShi Dong, Tengyu Ma, Benjamin Van Roy
On the Performance of Thompson Sampling on Logistic Bandits
5:00 PMYingkai Li, Yining Wang, Yuan Zhou
Nearly Minimax-Optimal Regret for Linearly Parameterized Bandits
5:10 PMDaniele Calandriello, Luigi Carratino, Alessandro Lazaric, Michal Valko, Lorenzo Rosasco
Gaussian Process Optimization with Adaptive Sketching: Scalable and No Regret
5:20 PMSébastien Bubeck, Yuanzhi Li, Haipeng Luo, Chen-Yu Wei
Improved Path-length Regret Bounds for Bandits
5:30 PMAkshay Krishnamurthy, John Langford, Aleksandrs Slivkins, Chicheng Zhang
Contextual Bandits with Continuous Actions: Smoothing, Zooming, and Adapting
5:40 PMYifang Chen, Chung-Wei Lee, Haipeng Luo, Chen-Yu Wei
A New Algorithm for Non-stationary Contextual Bandits: Efficient, Optimal, and Parameter-free
Peter Auer, Pratik Gajane, and Ronald Ortner
Adaptively Tracking the Best Bandit Arm with an Unknown Number of Distribution Changes
5:50 PMWojciech Kotlowski, Gergely Neu
Bandit Principal Component Analysis
Poster Session 2
6:00 PMPoster session 2
  1. Planting trees in graphs, and finding them back
  2. Reconstructing Trees from Traces
  3. Robustness of spectral methods for community detection
  4. Achieving the Bayes Error Rate in Stochastic Block Model by SDP, Robustly
  5. Optimal Learning for Mallows Block Model
  6. Accuracy-Memory Tradeoffs and Phase Transitions in Belief Propagation
  7. Learning Ising Models with Independent Failures
  8. Learning rates for Gaussian mixtures under group invariance
  9. Global Convergence of the EM Algorithm for Mixtures of Two Component Linear Regression
  10. Adaptive Hard Thresholding for Near-optimal Consistent Robust Regression
  11. Computationally and Statistically Efficient Truncated Regression
  12. The All-or-Nothing Phenomenon in Sparse Linear Regression
  13. The implicit bias of gradient descent on nonseparable data
  14. How do infinite width bounded norm networks look in function space?
  15. Mean-field theory of two-layers neural networks: dimension-free bounds and kernel limit
  16. Learning Neural Networks with Two Nonlinear Layers in Polynomial Time
  17. Learning Two Layer Rectified Neural Networks in Polynomial Time
  18. Gradient Descent for One-Hidden-Layer Neural Networks: Polynomial Convergence and SQ Lower Bounds
  19. Exponential Convergence Time of Gradient Descent for One-Dimensional Deep Linear Neural Networks
  20. Depth Separations in Neural Networks: What is Actually Being Separated?
  21. Stochastic Gradient Descent Learns State Equations with Nonlinear Activations
  22. An Information-Theoretic Approach to Minimax Regret in Partial Monitoring
  23. Sample complexity of partition identification using multi-armed bandits
  24. Batch-Size Independent Regret Bounds for the Combinatorial Multi-Armed Bandit Problem
  25. Multi-armed Bandit Problems with Strategic Arms
  26. Better Algorithms for Stochastic Bandits with Adversarial Corruptions
  27. On the Performance of Thompson Sampling on Logistic Bandits
  28. Nearly Minimax-Optimal Regret for Linearly Parameterized Bandits
  29. Gaussian Process Optimization with Adaptive Sketching: Scalable and No Regre
  30. Improved Path-length Regret Bounds for Bandits
  31. Contextual Bandits with Continuous Actions: Smoothing, Zooming, and Adapting
  32. A New Algorithm for Non-stationary Contextual Bandits: Efficient, Optimal, and Parameter-free
  33. Adaptively Tracking the Best Bandit Arm with an Unknown Number of Distribution Changes
  34. Bandit Principal Component Analysis
  35. Estimating the Mixing Time of Ergodic Markov Chains
  36. Distribution-Dependent Analysis of Gibbs-ERM Principle
  37. Theoretical guarantees for sampling and inference in generative models with latent diffusions
  38. Sampling and Optimization on Convex Sets in Riemannian Manifolds of Non-Negative Curvature
  39. Nonconvex sampling with the Metropolis-adjusted Langevin algorithm
  40. Normal Approximation for Stochastic Gradient Descent via Non-Asymptotic Rates of Martingale CLT
Conference Dinner
7:30 PMConference dinner in 120A
Thursday June 27
Continental Breakfast (8:15 AM -- 9:00AM)
Session 7 (Active Learning, Experimental Design, and Exploration)
9:00 AMTongyi Cao, Akshay Krishnamurthy
Disagreement-Based Combinatorial Pure Exploration: Sample Complexity Bounds and an Efficient Algorithm
9:10 AMXue Chen, Eric Price
Active Regression via Linear-Sample Sparsification
9:20 AMVivek Madan, Mohit Singh, Uthaipon Tantipongpipat, Weijun Xie
Combinatorial Algorithms for Optimal Design
9:30 AMMichal Derezinski, Kenneth L. Clarkson, Michael W. Mahoney, Manfred K. Warmuth
Minimax experimental design: Bridging the gap between statistical and worst-case approaches to least squares regression
9:40 AMMark Braverman, Jieming Mao, Yuval Peres
Sorted Top-k in Rounds
Keynote Talk 1
10:00 AMMoritz Hardt
TBD
Coffee Break (11:00 AM) / FCRC Keynote (11:20 AM) / Lunch (12:30 PM)
Open Problems Session
1:30 PMOpen problems
Session 8 (Privacy and Robustness)
2:10 PMAkshay Degwekar, Preetum Nakkiran, Vinod Vaikuntanathan
Computational Limitations in Robust Classification and Win-Win Results
2:20 PMOmar Montasser, Steve Hanneke, Nathan Srebro
VC Classes are Adversarially Robustly Learnable, but Only Improperly
2:30 PMYu Cheng, Ilias Diakonikolas, Rong Ge, David P. Woodruff
Faster Algorithms for High-Dimensional Robust Covariance Estimation
2:40 PMDylan Foster, Vasilis Syrgkanis
Statistical Learning with a Nuisance Component
2:50 PMGautam Kamath, Jerry Li, Vikrant Singhal, Jonathan Ullman
Privately Learning High-Dimensional Distributions
3:00 PMJohn Duchi, Ryan Rogers
Lower Bounds for Locally Private Estimation via Communication Complexity
3:10 PMAmos Beimel, Shay Moran, Kobbi NIssim, Uri Stemmer
Private Center Points and Learning of Halfspaces
3:20 PMKwang-Sung Jun, Francesco Orabona
Parameter-free Online Convex Optimization with Sub-Exponential Noise
Afternoon Break (3:30 PM)
Session 9 (Optimization)
4:00 PMNicholas J. A. Harvey, Christopher Liaw, Yaniv Plan, Sikander Randhawa
Tight analyses for non smooth stochastic gradient descent
4:10 PMPrateek Jain, Dheeraj Nagaraj, Praneeth Netrapalli
Making the Last Iterate of SGD Information Theoretically Optimal
4:20 PMLijun Zhang, Zhi-Hua Zhou
Stochastic Approximation of Smooth and Strongly Convex Functions: Beyond the $O(1/T)$ Convergence Rate
4:30 PMBo Jiang, Haoyue Wang, Shuzhong Zhang
An Optimal High-Order Tensor Method for Convex Optimization
Sebastien Bubeck, Qijia Jiang, Yin Tat Lee, Yuanzhi Li, Aaron Sidford
Near-optimal method for highly smooth convex optimization
Alexander Gasnikov, Pavel Dvurechensky, Eduard Gorbunov, Evgeniya Vorontsova, Daniil Selikhanovych, Cesar A. Uribe
Optimal Tensor Methods in Smooth Convex and Uniformly Convex Optimization
4:40 PMAdrien Taylor, Francis Bach
Stochastic first-order methods: non-asymptotic and computer-aided analyses via potential functions
4:50 PMUlysse Marteau-Ferey, Dmitrii M. Ostrovskii, Francis Bach, Alessandro Rudi
Beyond Least-Squares: Fast Rates for Regularized Empirical Risk Minimization through Self-Concordance
5:00 PMYin Tat Lee, Zhao Song, Qiuyi Zhang
Solving Empirical Risk Minimization in the Current Matrix Multiplication Time
5:10 PMJelena Diakonikolas, Cristóbal Guzmán
Lower Bounds for Parallel and Randomized Convex Optimization
5:20 PMDylan Foster, Ayush Sekhari, Ohad Shamir, Nathan Srebro, Karthik Sridharan, Blake Woodworth
The Complexity of Making the Gradient Small in Stochastic Convex Optimization
5:30 PMFrancis Bach, Kfir Y. Levy
A Universal Algorithm for Variational Inequalities Adaptive to Smoothness and Noise
5:40 PMRong Ge, Zhize Li, Weiyao Wang, Xiang Wang
Stabilized SVRG: Simple Variance Reduction for Nonconvex Optimization
5:50 PMCong Fang, Zhouchen Lin, Tong Zhang
Sharp Analysis for Nonconvex SGD Escaping from Saddle Points
Poster Session 3
6:00 PMPoster session 3
  1. The Relative Complexity of Maximum Likelihood Estimation, MAP Estimation, and Sampling
  2. Disagreement-Based Combinatorial Pure Exploration: Sample Complexity Bounds and an Efficient Algorithm
  3. Active Regression via Linear-Sample Sparsification
  4. Combinatorial Algorithms for Optimal Design
  5. Minimax experimental design: Bridging the gap between statistical and worst-case approaches to least squares regression
  6. Sorted Top-k in Rounds
  7. Computational Limitations in Robust Classification and Win-Win Results
  8. VC Classes are Adversarially Robustly Learnable, but Only Improperly
  9. Faster Algorithms for High-Dimensional Robust Covariance Estimation
  10. Statistical Learning with a Nuisance Component
  11. Privately Learning High-Dimensional Distributions
  12. Lower Bounds for Locally Private Estimation via Communication Complexity
  13. Private Center Points and Learning of Halfspaces
  14. Parameter-free Online Convex Optimization with Sub-Exponential Noise
  15. Tight analyses for non smooth stochastic gradient descent
  16. Making the Last Iterate of SGD Information Theoretically Optimal
  17. Stochastic Approximation of Smooth and Strongly Convex Functions: Beyond the $O(1/T)$ Convergence Rate
  18. An Optimal High-Order Tensor Method for Convex Optimization
  19. Near-optimal method for highly smooth convex optimization
  20. Optimal Tensor Methods in Smooth Convex and Uniformly Convex Optimization
  21. Stochastic first-order methods: non-asymptotic and computer-aided analyses via potential functions
  22. Beyond Least-Squares: Fast Rates for Regularized Empirical Risk Minimization through Self-Concordance
  23. Solving Empirical Risk Minimization in the Current Matrix Multiplication Time
  24. Lower Bounds for Parallel and Randomized Convex Optimization
  25. The Complexity of Making the Gradient Small in Stochastic Convex Optimization
  26. A Universal Algorithm for Variational Inequalities Adaptive to Smoothness and Noise
  27. Stabilized SVRG: Simple Variance Reduction for Nonconvex Optimization
  28. Sharp Analysis for Nonconvex SGD Escaping from Saddle Points
  29. Uniform concentration and symmetrization for weak interactions
  30. Learning from Weakly Dependent Data under Dobrushin's Condition
  31. High probability generalization bounds for uniformly stable algorithms with nearly optimal rate
  32. When can unlabeled data improve the learning rate?
  33. Classification with unknown class conditional label noise on non-compact feature spaces
  34. Consistency of Interpolation with Laplace Kernels is a High-Dimensional Phenomenon
  35. On Communication Complexity of Classification Problems
  36. Space lower bounds for linear prediction in the streaming model
  37. Affine Invariant Covariance Estimation for Heavy-Tailed Distributions
  38. Approximate Guarantees for Dictionary Learning
  39. Sample-Optimal Low-Rank Approximation of Distance Matrices
  40. A near-optimal algorithm for approximating the John Ellipsoid
Friday June 28
Continental Breakfast (8:15 AM -- 9:00AM)
Session 10 (Reinforcement Learning and Control)
9:00 AMMax Simchowitz, Ross Boczar, Benjamin Recht
Learning Linear Dynamical Systems with Semi-Parametric Least Squares
9:10 AMR. Srikant, Lei Ying
Finite-Time Error Bounds For Linear Stochastic Approximation and TD Learning
9:20 AMWen Sun, Nan Jiang, Akshay Krishnamurthy, Alekh Agarwal, John Langford
Model-based RL in Contextual Decision Processes: PAC bounds and Exponential Improvements over Model-free Approaches
9:30 AMBelhal Karimi, Blazej Miasojedow, Eric Moulines, Hoi-To Wai
Non-asymptotic Analysis of Biased Stochastic Approximation Scheme
9:40 AMStephen Tu, Benjamin Recht
The Gap Between Model-Based and Model-Free Methods on the Linear Quadratic Regulator: An Asymptotic Viewpoint
Coffee Break (11:00 AM) / FCRC Keynote (11:20 AM) / Lunch (12:30 PM)
Business Meeting
1:30 PMBusiness meeting
Afternoon Break (3:30 PM)
Session 12 (Statistical Learning Theory and Algorithms)
4:00 PMAndreas Maurer, Massimiliano Pontil
Uniform concentration and symmetrization for weak interactions
4:10 PMYuval Dagan, Constantinos Daskalakis, Nishanth Dikkala, Siddhartha Jayanti
Learning from Weakly Dependent Data under Dobrushin's Condition
4:20 PMVitaly Feldman, Jan Vondrak
High probability generalization bounds for uniformly stable algorithms with nearly optimal rate
4:30 PMChristina Göpfert, Shai Ben-David, Olivier Bousquet, Sylvain Gelly, Ilya Tolstikhin, Ruth Urner
When can unlabeled data improve the learning rate?
4:40 PMHenry Reeve, Ata Kaban
Classification with unknown class conditional label noise on non-compact feature spaces
4:50 PMAlexander Rakhlin, Xiyu Zhai
Consistency of Interpolation with Laplace Kernels is a High-Dimensional Phenomenon
5:00 PMDaniel Kane, Roi Livni, Shay Moran, Amir Yehudayoff
On Communication Complexity of Classification Problems
5:10 PMYuval Dagan, Gil Kur, Ohad Shamir
Space lower bounds for linear prediction in the streaming model
5:20 PMDmitrii M. Ostrovskii, Alessandro Rudi
Affine Invariant Covariance Estimation for Heavy-Tailed Distributions
5:30 PMAditya Bhaskara, Wai Ming Tai
Approximate Guarantees for Dictionary Learning
5:40 PMPiotr Indyk, Ali Vakilian, Tal Wagner, David Woodruff
Sample-Optimal Low-Rank Approximation of Distance Matrices
5:50 PMMichael B. Cohen, Ben Cousins, Yin Tat Lee, Xin Yang
A near-optimal algorithm for approximating the John Ellipsoid
Impromptu Session
6:00 PMImpromptu talks