Program for Wednesday, September 28th: Talk View

PROGRAM FOR WEDNESDAY, SEPTEMBER 28TH: TALK VIEW

Days:

next day

all days

View: with abstracts session overview

8:30

9:00

9:30

10:00

10:30

11:00

11:30

12:00

12:30

13:00

13:30

14:00

14:30

15:00

15:30

16:00

16:30

17:00

08:30-10:10

Convex Parameterization of Stabilizing Controllers and its LMI-based Computation via Filtering

Mauricio C. de Oliveira, Yang Zheng

08:30-10:10

Regularized Gradient Descent Ascent for Two-Player Zero-Sum Markov Games

Thinh Doan

08:30-10:10

TaSIL: Taylor Series Imitation Learning

Daniel Pfrommer, Thomas Zhang, Stephen Tu, Nikolai Matni

08:30-10:10

Optimal Private Data Acquisition: Central and Local Differential Privacy

Alireza Fallah, Ali Makhdoumi, Azarakhsh Malekian, Asu Ozdaglar

08:30-10:10

Leave-one-out Singular Subspace Perturbation Analysis for Spectral Clustering

Anderson Ye Zhang, Harrison H Zhou

08:30-10:10

Near-optimal algorithms for Imitation Learning

Nived Rajaraman, Yanjun Han, Lin F. Yang, Kannan Ramchandran, Jiantao Jiao

08:30-10:10

Selecting the Number of Communities in Count-Weighted Networks

Yucheng Liu, Xiaodong Li

08:30-10:10

Active Learning for Individual Data via Minimal Stochastic Complexity

Shachar Shayovitz, Meir Feder

08:30-10:10

Byzantine Resilience With Reputation Scores

Jayanth Regatti, Hao Chen, Abhishek Gupta

08:30-10:10

CoBAAF: Controlled Bayesian Air Aggregation Federated Learning from Heterogeneous Data

Tomer Gafni, Kobi Cohen, Yonina Eldar

08:30-10:10

Ensuring the Defense of Paths and Perimeters in Dynamic Defender-Attacker Blotto Games (dDAB) on

Bryce Ferguson, Daigo Shishika, Jason Marden

08:30-10:10

Over-the-Air Federated Learning with Privacy Protection via Correlated Additive Perturbations

Jialing Liao, Zheng Chen, Erik G. Larsson

08:30-10:10

Permutation Codes for Correcting a Burst of at Most $t$ Deletions

Shuche Wang, Yuanyuan Tang, Ryan Gabrys, Farzad Farnoud

08:30-10:10

Bounds on Reversible, Complement, Reversible-Complement, Constant Weight Sum Codes

Krishna Gopal Benerjee, Adrish Banerjee

08:30-10:10

Zero-error Coding for Computing with Encoder Side-information

Nicolas Charpenay, Maël Le Treust, Aline Roumy

08:30-10:10

Extracting Unique Information Through Markov Relations

Keerthana Gurushankar, Praveen Venkatesh, Pulkit Grover

08:30-10:10

Strategic Communication via Cascade Multiple-Description Network

Rony Bou Rouphael, Maël Le Treust

10:10-10:30 Break

10:30-12:30

Momentum-Based Learning and Optimization Dynamics with Stochastic Restarting

Jorge I. Poveda

10:30-12:30

Stability and Safety Constrained Reinforcement Learning for Voltage Control

Yuanyuan Shi

10:30-12:30

Representation-assisted Reinforcement Learning under Distribution Shift

Yuan Cheng, Jing Yang, Yingbin Liang

10:30-12:30

Mixed Strategies with Finite Support in Continuous Spaces: A Case Study in Trajectory Games

David Fridovich-Keil

10:30-12:30

Quickest Detection of the Change of Community via Stochastic Block Models

Fei Sha, Ruizhi Zhang

10:30-12:30

Spatio-temporal Multiple Change-point Detection in Sensor Networks

Topi Halme, Eyal Nitzan, Visa Koivunen

10:30-12:30

Quickest Detection of a Threat to an Impending Disaster

Tim Brucks, Taposh Banerjee, Rahul Mishra

10:30-12:30

Online detection of cascading change-points using diffusion networks

Rui Zhang, Yao Xie, Rui Yao, Feng Qiu

10:30-12:30

Window-Limited CUSUM for Sequential Change Detection

Liyan Xie, George Moustakides, Yao Xie

10:30-12:30

Decentralized Cooperative Reinforcement Learning with Hierarchical Information Structure

Hsu Kao, Chen-Yu Wei, Vijay Subramanian

10:30-12:30

Bandits with Dynamic Arm-acquisition Costs

Anand Kalvit, Assaf Zeevi

10:30-12:30

A Survey of Dynamic Watermarking Algorithms and Some Recent Developments

Jiacheng Tang, Abhishek Gupta

10:30-12:30

Leveraging Spatial and Temporal Correlations in Distributed Learning

Divyansh Jhunjhunwala, Ankur Mallick, Gauri Joshi

10:30-12:30

Uncertainty in Biometric Identification and Authentication Systems with Strong Secrecy

Linghui Zhou, Tobias Oechtering, Mikael Skoglund

10:30-12:30

Linear Coding for Gaussian Two-Way Channels

J. Kim, S. Hosseinalipour, T. Kim, D. Love, C. Brinton

10:30-12:30

Finite-Blocklength Results for the A-channel: Applications to Unsourced Random Access and Group

Alejandro Lancho, Alexander Fengler, Yury Polyanskiy

10:30-12:30

On the Symmetries of the Deletion Channel

Francisco Pernice

12:30-13:30 Lunch

13:30-15:10

Beyond No Regret: Instance-Dependent PAC Reinforcement Learning

Andrew Wagenmaker, Max Simchowitz, Kevin Jamieson

13:30-15:10

Repeated Games, Optimal Channel Capture, and Open Problems for Slotted Multiple Access

Michael J. Neely

13:30-15:10

The Multisecretary Problem: Regret, Approximation and Learning

Siddhartha Banerjee

13:30-15:10

Markovian Interference in Experiments

Vivek Farias

13:30-15:10

Efficient SPRT-based Best Arm Identification in Stochastic Bandits

Arpan Mukherjee, Ali Tajer

13:30-15:10

Efficient sequential UCB-based Hungarian algorithm for assignment problems

Yuyang Shi, Yajun Mei

13:30-15:10

Data-Driven Sequential Change Detection in Privacy-Sensitive Networks

Mehmet Necip Kurt, Yasin Yilmaz, Xiaodong Wang, Pieter J. Mosterman

13:30-15:10

Decentralized Anomaly Detection via Deep Multi-Agent Reinforcement Learning

Hadar Szostak, Kobi Cohen

13:30-15:10

Oversquashing in GNNs through the lens of information contraction and graph expansion

Pradeep Kr. Banerjee, Kedar Karhadkar, Yu Guang Wang, Uri Alon, Guido Montufar

13:30-15:10

Classifying Incomplete Data with a Mixture of Subspace Experts

Ben Kizaric, Daniel Pimentel-Alarcon

13:30-15:10

Multivariate Feature Extraction

Xiangxiang Xu, Lizhong Zheng

13:30-15:10

On Sample Complexity of Learning Shared Representations: The Asymptotic Regime

Xinyi Tong, Xiangxiang Xu, Shao-Lun Huang

13:30-15:10

Distributed Consensus-based Kalman Filter under Limited Communication

Diego Benalcazar, Chinwendu Enyioha

13:30-15:10

Decentralized Online Influence Maximization

Yigit Ege Bayiz, Ufuk Topcu

13:30-15:10

Learning-based Optimal Admission Control in a Single Server Queuing System

Yili Zhang, Asaf Cohen, Vijay Subramanian

13:30-15:10

Trimmed Minimum Error Entropy for Robust Online Regression

Sajjad Bahrami, Ertem Tuncel

13:30-15:10

May the force be with you

Yulan Zhang, Anna Gilbert, Stefan Steinerberger

13:30-15:10

Reachability of Chen-Fliess series: A Gradient Descent Approach

Ivan Perez Avellaneda, Luis Duffaut Espinosa

15:10-15:30 Break

15:30-17:10

Schedule Based Temporal Difference Algorithms

Rohan Deb, Meet Gandhi, Shalabh Bhatnagar

15:30-17:10

A concentration bound for distributed stochastic approximation

Harsh Dolhare, Vivek Borkar

15:30-17:10

Global Convergence of Federated Learning for Mixed Regression

Lili Su, Jiaming Xu, Pengkun Yang

15:30-17:10

Exploration, Exploitation, and Engagement in Multi-Armed Bandits with Abandonment

Zixian Yang, Xin Liu, Lei Ying

15:30-17:10

On representation learning with Model-Agnostic Meta-Learning

Liam Collins, Aryan Mokhtari, Sewoong Oh, Sanjay Shakkottai

15:30-17:10

A distributionally robust approach to domain adaptation

Akram Awad, George Atia

15:30-17:10

Policy Gradient Method For Robust Reinforcement Learning

Yue Wang, Shaofeng Zou

15:30-17:10

Post-hoc Uncertainty Learning using a Dirichlet Meta-Model

M. Shen, Y. Bu, P. Sattigeri, S. Ghosh, S. Das, G. Wornell

15:30-17:10

Quickest Detection with Anticipatory and Quantum Decision Makers

Vikram Krishnamurthy, Luke Snow, Brian Sadler

15:30-17:10

Policy Gradient based Entropic-VaR Optimization in Risk-Sensitive Reinforcement Learning

Xinyi Ni, Lifeng Lai

15:30-17:10

The Inverse Problem of Linear-Quadratic Differential Games: When is a Control Strategies Profile

Yunhan Huang, Tao Zhang, Quanyan Zhu

15:30-17:10

Adversarial Examples for Model-Based Control: A Sensitivity Analysis

Po-Han Li, Ufuk Topcu, Sandeep Chinchali

15:30-17:10

System Identification Entropy for Chen-Fliess Series and Their Interconnections

W. Steven Gray

15:30-17:10

Risk-Aware Safe Optimal Control of Uncertain Linear Systems

Pouria Tooranjipour, Bahare Kiumarsi, Hamidreza Modares

15:30-17:10

Beyond UCB: statistical complexity and optimal algorithm for non-linear ridge bandits

Yanjun Han, Jiantao Jiao, Nived Rajaraman, Kannan Ramchandran

15:30-17:10

Queueing Delay Minimization in Overloaded Networks via Rate Control

Xinyu Wu, Dan Wu, Eytan Modiano

15:30-17:10

Age of Information Process under Strongly Mixing Communication -- Moment Bound, Mixing Rate and Strong

Adrian Redder, Arunselvan Ramaswamy, Holger Karl

15:30-17:10

ASUMAN: Age Sense Updating Multiple Access in Networks

Purbesh Mitra, Sennur Ulukus

15:30-17:10

Universal Policy Tracking: Scheduling for Wireless Networks with Delayed State Observation

Bai Liu, Eytan Modiano

15:30-17:10

Pricing, competition and market segmentation in ride hailing

Tushar Shankar Walunj, Shiksha Singhal, Veeraruna Kavitha, Jayakrishnan Nair