Name: Competitive Control via Online Optimization
Start: 2020-10-08T16:00:00-04:00
End: 2020-10-08T17:00:00-04:00
Location: Remote/Virtual

Feb 9

9:15 am - 10:15 am

Understanding the Universality Phenomenon in High- Dimensional Estimation and Learning: Some Recent Progress

1690 Beyster Building 2260 Hayward Street, Ann Arbor

Event Details Get Directions

Events

Data-Analytic Opportunities and Challenges in Solar Eruption Forecasting

Edge and IoT-supported Intelligent Augmented Reality: Promise, Challenges, and Solutions

Cancelled

Distributed learning on correlated data with communication constraints

Image Restoration through Inversion by Direct Iteration (InDI)

Formal privacy guarantees for optimization datasets in power systems

Select Topics Associated with 3D Scanning by Means of Structured Light Illumination

Re-engineering the Uplink for Next Generation Multiple Access

On False Positive Error

Foundation Models AAA: Acceleration, Application, Adversary

Transfer learning for contextual multi-armed bandits

Accelerated Optimization for Dynamic MRI Reconstruction with Locally Low-Rank Regularizers

Towards a Theoretical Understanding of Parameter-Efficient Fine-Tuning (and Beyond)

Flat Minima Generalize for Low-Rank Matrix Recovery

(CANCELED) Discrete Optimization for Adversarial Attacks on Large Language Models

Rethinking the theoretical foundation of reinforcement learning

Sparsity for Efficient Long Sequence Generation of LLMs

Overparameterization and Global Optimality in Nonconvex Low-Rank Matrix Estimation and Optimization

Breaking the Sample Size Barrier in Reinforcement Learning via Model-Based Algorithms

How Hessian Structure Explains Mysteries in Sharpness Regularization

Theoretical Characterization of Forgetting and Generalization of Continual Learning

Transformers as Support Vector Machines

Wireless is back: The 6G Revolution Towards Connected Intelligence

Solving Inverse Problems with Latent Diffusion Models via Hard Data Consistency

Integrated Sensing and Communication: aspects from Information Theory, Communication Theory, and Machine Learning

Quantum Signal Processing

On an Asymptotic Criterion for Blockchain Design

On the Emergence of Invariant Low-Dimensional Subspaces in Gradient Descent for Learning Deep Networks

Setup Times in Multiserver Systems

Demystifying and Mitigating Unfairness for Machine Learning over Graphs

Machine Learning challenges in Metrology in Semiconductor Device Industry

Best of three worlds? Bias and extrapolation in constant-step size stochastic approximation

Deep Learning Meets Sparse Regularization: A Signal Processing Perspective

Explainable AI via Semantic Information Pursuit

Load Balancing under Data Locality: Extending Mean-Field Framework to Constrained Large-Scale Systems

Implicit Geometry of Large Classification Models: Imbalance Trouble

Cancelled: Implicit Geometry of Large Classification Models: Imbalance Trouble

Evaluating Unsupervised Denoising Requires Unsupervised Metrics

Understanding the Universality Phenomenon in High- Dimensional Estimation and Learning: Some Recent Progress

Reinforcement Learning with Robustness and Safety Guarantees

Dynamic Pricing and Matching for Online Marketplaces

Deep Networks and the Multiple Manifold Problem

Advancing Machine Learning for Imaging: Regularization and Robustness

Opportunistic Integrated Communication and Weather Sensing

Accelerating Ill-conditioned Low-rank Estimation via Scaled Gradient Descent

Sparse Neural Networks: From Practice to Theory

Method of Moments: From Sample Complexity to Efficient Implicit Computations

A New Embedding Framework to Design Consistent Surrogate Losses

Robust Learning by Double Over-Parameterization

Principles of Deep Representation Learning via Neural Collapse

Blessing of Nonconvexity in Factorized Models

KO Codes

Surprises in High-Dimensional (Overparameterized) Linear Classification

Sequential Decision Making: How Much Adaptivity Is Needed Anyways?

Data-driven and Learning-based Methods for Control: Challenges and New Horizons

Data-Centric Networking: Theory, Algorithms and Applications

Generalization and Inductive Bias in Neural Networks

Finding Global Minima via Kernel Approximations

Learning More from the Past: Offline Batch RL

Spectrum Sharing for 5G and Beyond: A Network Economics View

Interactive Communications

Communication and Sensing: From Compressed Sampling to Model-based Deep Learning

Social Learning in Multi-Agent, Multi-Armed Bandits

Secure Model Aggregation in Federated Learning

Database Alignment: Fundamental Limits and Efficient Algorithms

Towards Model Agnostic Robustness

The Power of Exploiter: Provable Multi-Agent RL in Large State Spaces

How to Schedule Near-Optimally under Real-World Constraints

Multiclass and Multi-Label Learning with General Losses: What is the Right Output Coding and Decoding?

Deep Networks from First Principles

Adaptive Design of Switchback Experiments: A Markov Chain Perspective