Conference Schedule

Video recordings of the talks can be found here.

Below is a schedule for the conference. All times are in Singapore time (SGT). All talks will be in Seminar Room 1, in building COM1 at the School of Computing, National University of Singapore.

Please note that session titles are meant to provide a loose theme for the majority of papers in a session, individual papers may not always fit the given topic exactly.

FEBRUARY 20, 2023
9:10-9:30 AMWelcome notes (Shipra Agrawal and Francesco Orabona)
9:30-10:30 AMSession 1 (High dimensional Statistics) (Chair: Pierre Alquier)
SQ Lower Bounds for Random Sparse Planted Vector Problem,
Hua, Yiding*; Ding, Jingqiu
Spectral Subspace Dictionary Learning,
White, Stephen E*; Novikov, Alexei
Universal Bias Reduction in Estimation of Smooth Additive Function in High Dimensions, (virtual)
Zhou, Fan*; Li, Ping; Zhang, Cun-Hui
11:00 AM-12:00 PMSession 2 (Online Learning) (Chair: Gergely Neu)
Spatially Adaptive Online Prediction of Piecewise Regular Functions, (virtual)
Chatterjee, Sabyasachi*; Goswami, Subhajit
Perceptronic Complexity and Online Matrix Completion,
Pasteris, Stephen U*
Online Self-Concordant and Relatively Smooth Minimization With Applications to Online Portfolio Selection and Learning Quantum States,
Tsai, Chung-En; Cheng, Hao-Chung; Li, Yen-Huan*
2:00-3:00 PMPlenary talk, Matus Telgarsky
3:30-4:30 PMSession 3 (Statistics) (Chair: Umut Simsekli)
Testing Tail Weight of a Distribution Via Hazard Rate,
Aliakbarpour, Maryam; Biswas, Amartya; Ravichandran, Kavya*; Rubinfeld, Ronitt
Towards Empirical Process Theory for Vector-Valued Functions: Metric Entropy of Smooth Function Classes,
Park, Junhyung*; Muandet, Krikamol
Adaptive Power Method: Eigenvector Estimation from Sampled Data,
Shin, Seiyun*; Zhao, Han; Shomorony, Ilan
5:00-6:00 PMSession 4 (Neural Networks and related) (Chair: Adil Salim)
Implicit Regularization Towards Rank Minimization in ReLU Networks,
Timor, Nadav*; Vardi, Gal; Shamir, Ohad
On The Computational Complexity of Self-Attention,
Duman Keles, Feyza; Wijewardena, Maheshakya; Hegde, Chinmay*
Convergence of score-based generative modeling for general data distributions,
Lee, Holden*; Lu, Jianfeng; Tan, Yixin
6:30-9:30 PMRECEPTION (NUSS Kent Ridge Guild House)


FEBRUARY 21, 2023
9:30-10:30 AMSession 1 (Reinforcement Learning) (Chair: Krikamol Muandet)
Variance-Reduced Conservative Policy Iteration, (virtual)
Agarwal, Naman*; Bullins, Brian; Singh, Karan
Linear Reinforcement Learning with Ball Structure Action Space, (virtual)
Jia, Zeyu*; Jia, Randy; Madeka, Dhruv; Foster, Dean
Optimistic PAC Reinforcement Learning: the Instance-Dependent View,
Tirinzoni, Andrea; Al Marjani, Aymen; Kaufmann, Emilie*
11:00 AM-12:00 PMSession 2 (Online Learning) (Chair: Nishant Mehta)
Constant regret for sequence prediction with limited advice,
Saad, El Mehdi*; Blanchard, Gilles
Pseudonorm Approachability and Applications to Regret Minimization,
Dann, Chris; Mansour, Yishay; Mohri, Mehryar; Schneider, Jon; Sivan, Balasubramanian*
On Computable Online Learning (Best Paper Award),
Hasrati, Niki*; Ben-David, Shai
12:00-2:00 PMWomen In Learning Theory Lunch (COM3-02-59 aka Meeting Room 20)
2:00-3:00 PMPlenary talk, Vladimir Vovk
3:30-4:30 PMSession 3 (Multi-armed bandits) (Chair: Julian Zimmert)
On Best-Arm Identification with a Fixed Budget in Non-Parametric Multi-Armed Bandits,
Barrier, Antoine; Garivier, Aurélien; Stoltz, Gilles*
Dealing with Unknown Variances in Best-Arm Identification,
Jourdan, Marc*; Degenne, Rémy; Kaufmann, Emilie
Max-Quantile Grouped Infinite-Arm Bandits,
Lau, Ivan; Ling, Yan Hao; Shrivastava , Mayank ; Scarlett, Jonathan*
5:00-6:00 PMSession 4 (Robust Learning) (Chair: Jonathan Scarlett)
Adversarially Robust Learning with Tolerance,
Ashtiani, Hassan; Pathak, Vinayak*; Urner, Ruth
Robust Estimation of Discrete Distributions under Local Differential Privacy,
Chhor, Julien*; Sentenac, Flore
Robust Empirical Risk Minimization with Tolerance,
Bhattacharjee, Robi*; Hopkins, Max; Kumar, Akash; Yu, Hantao; Chaudhuri, Kamalika


FEBRUARY 22, 2023
9:30-10:30 AMSession 1 (Reinforcement Learning) (Chair: Matteo Papini)
Efficient Global Planning in Large MDPs via Stochastic Primal-Dual Optimization,
Neu, Gergely; Okolo, Nneka M*
Adversarial Online Multi-Task Reinforcement Learning,
Nguyen, Quan M*; Mehta, Nishant
A Unified Algorithm for Stochastic Path Problems,
Dann, Chris*; Wei, Chen-Yu; Zimmert, Julian
11:00 AM-12:00 PMSession 2 (Online Learning) (Chair: Shipra Agrawal)
Reaching Goals is Hard: Settling the Sample Complexity of the Stochastic Shortest Path,
Chen, Liyu*; Tirinzoni, Andrea; Pirotta, Matteo; Lazaric, Alessandro
Online Learning with Off-Policy Feedback,
Gabbianelli, Germano*; Neu, Gergely; Papini, Matteo
Projection-free Adaptive Regret with Membership Oracles, (virtual)
Lu, Zhou*; Brukhim, Nataly; Gradu, Paula; Hazan, Elad
1:30-2:30 PMPlenary talk, Nika Haghtalab
3:00-4:00 PMSession 3 (Multi-armed bandits) (Chair: Nika Haghtalab)
Follow-the-Perturbed-Leader Achieves Best-of-Both-Worlds for Bandit Problems,
Honda, Junya*; Ito, Shinji; Tsuchiya, Taira
Best-of-Both-Worlds Algorithms for Partial Monitoring,
Tsuchiya, Taira*; Ito, Shinji; Honda, Junya
Improved High-Probability Regret for Adversarial Bandits with Time-Varying Feedback Graphs, (virtual)
Luo, Haipeng; Tong, Hanghang; Zhang, Mengxiao*; Zhang, Yuheng
4:30-5:30 PMSession 4 (Generalization bounds) (Chair: Matus Telgarsky)
Algorithmic Stability of Heavy-Tailed Stochastic Gradient Descent on Least Squares,
Raj, Anant*; Barsbey, Melih; Gurbuzbalaban, Mert; Zhu, Lingjiong; Simsekli, Umut
Wide stochastic networks: Gaussian limit and PAC-Bayesian training,
Clerico, Eugenio*; Deligiannidis, George; Doucet, Arnaud
Limitations of Information-Theoretic Generalization Bounds for Gradient Descent Methods in Stochastic Convex Optimization,
Haghifam, Mahdi*; Rodríguez Gálvez, Borja; Thobaben, Ragnar; Skoglund, Mikael; Roy, Daniel M.; Dziugaite, Gintare Karolina
6:30-9:30 PMBANQUET (Singapore Night Safari)


FEBRUARY 23, 2023
9:30-10:30 AMSession 1 (Combinatorial) (Chair: Pierre Alquier)
Tournaments, Johnson Graphs and NC-Teaching,
Simon, Hans U*
Reconstructing Ultrametric Trees from Noisy Experiments,
Arunachaleswaran, Eshwar Ram*; Kannan, Sampath; De, Anindya
A Query Algorithm for Learning a Spanning Forest in Weighted Undirected Graphs, (virtual)
Liao, Hang*; Chakrabarty, Deeparnab
11:00 AM-12:00 PMSession 2 (Online Learning) (Chair: Francesco Orabona)
Online k-means Clustering on Arbitrary Data Streams,
Bhattacharjee, Robi*; Imola, Jacob J; Moshkovitz, Michal; Dasgupta, Sanjoy
The Replicator Dynamic, Chain Components and the Response Graph,
Biggar, Oliver*; Shames, Iman
Primal-Dual Algorithms with Predictions for Online Bounded Allocation and Ad-Auctions Problems,
Nguyen, Kim Thang*; Kevi, Enikő
12:00 PM-1:00 PMBusiness Meeting
1:00 PM-2:00 PMCatered Lunch
2:00-3:00 PMPlenary talk, Taiji Suzuki
3:30-4:30 PMSession 3 (Multi-armed bandits) (Chair: Junya Honda)
An Instance-Dependent Analysis for the Cooperative Multi-Player Multi-Armed Bandit, (virtual)
Pacchiano, Aldo*; Bartlett, Peter; Jordan, Michael
Online Learning for Traffic Navigation in Congested Networks,
Gollapudi, Sreenivas; Kollias, Kostas; Maheshwari, Chinmay; Wu, Manxi*
Complexity Analysis of a Countable-armed Bandit Problem,
Kalvit, Anand*; Zeevi, Assaf
5:00-6:00 PMSession 4 (Optimization) (Chair: Hans Simon)
On the complexity of finding stationary points of smooth functions in one dimension (Best Student Paper Award),
Chewi, Sinho*; Bubeck, Sebastien; Salim, Adil
Private Stochastic Optimization with Large Worst-Case Lipschitz Parameter: Optimal Rates for (Non-Smooth) Convex Losses and Extension to Non-Convex Losses,
Lowy, Andrew*; Razaviyayn, Meisam
Fisher information lower bounds for sampling,
Chewi, Sinho; Gerber, Patrik R; Lee, Holden; Lu, Chen*

Welcome Reception Information

The welcome reception will be held at NUSS Kent Ridge Guild House.  This is a short walk from the conference venue, and we will lead you there shortly after the final Monday session.  Following Google Maps starting from the NUS School of Computing should also be straightforward.

The welcome reception includes:

  • Soft drinks
  • Limited amount of beer/wine
  • Cocktail buffet

Banquet Information

IMPORTANT: Please be very careful if you choose to make your own way back instead of using the bus provided.  If you plan to take public transport, note that it is a lengthy trip and be mindful of the MRT closing hours.  If you plan to take a taxi, note that these can be in extremely high demand from this area in the late evening.  The risk is highest if you don’t have phone/internet access (if you do, we suggest setting up the CDG taxi app in advance).

The banquet will be held at the Singapore Night Safari, and you are also given admission to the (nocturnal) zoo.  The full restaurant name and address is Ulu Court (Night Safari), 80 Mandai Lake Road Singapore 729826.

Buses will depart from the conference venue at around 5:45pm – please follow us to the lobby immediately after the final session (ending at 5:30pm).  

Buses returning from the banquet venue will depart at 9:30pm and 10:30pm, and will stop at 3 well-connected MRT stations: Dhoby Ghaut, Outram Park, and Buona Vista.  

  • Please note that the 10:30pm bus might arrive at Buona Vista MRT too late to catch a train, so a short taxi ride may still be needed.  If needed, you can walk 3 minutes to the Park Avenue Rochester Hotel and ask them to call one.