8 papers
Connecting Score Matching, Maximum Likelihood, and Expectation-Maximization in Mixed Linear Regression
Zhankun Luo, Abolfazl Hashemi
We study variance-preserving diffusion of the response in mixed linear regression (MLR) with unknown mixing weights. Our analysis separates the statistical guarantees of score matc…
Structural Properties, Cycloid Trajectories and Non-Asymptotic Guarantees of EM Algorithm for Mixed Linear Regression
Zhankun Luo, Abolfazl Hashemi
This work investigates the structural properties, cycloid trajectories, and non-asymptotic convergence guarantees of the Expectation-Maximization (EM) algorithm for two-component M…
Characterizing Evolution in Expectation-Maximization Estimates for Overspecified Mixed Linear Regression
Zhankun Luo, Abolfazl Hashemi
Mixture models have attracted significant attention due to practical effectiveness and comprehensive theoretical foundations. A persisting challenge is model misspecification, whic…
Learning to Localize Leakage of Cryptographic Sensitive Variables
Jimmy Gammell, Anand Raghunathan, Abolfazl Hashemi +1
While cryptographic algorithms such as the ubiquitous Advanced Encryption Standard (AES) are secure, *physical implementations* of these algorithms in hardware inevitably 'leak' se…
Unveiling the Cycloid Trajectory of EM Iterations in Mixed Linear Regression
Zhankun Luo, Abolfazl Hashemi
We study the trajectory of iterations and the convergence rates of the Expectation-Maximization (EM) algorithm for two-component Mixed Linear Regression (2MLR). The fundamental goa…
Optimistic Regret Bounds for Online Learning in Adversarial Markov Decision Processes
Sang Bin Moon, Abolfazl Hashemi
The Adversarial Markov Decision Process (AMDP) is a learning framework that deals with unknown and varying tasks in decision-making applications like robotics and recommendation sy…
AdaGossip: Adaptive Consensus Step-size for Decentralized Deep Learning with Communication Compression
Sai Aparna Aketi, Abolfazl Hashemi, Kaushik Roy
Decentralized learning is crucial in supporting on-device learning over large distributed datasets, eliminating the need for a central server. However, the communication overhead r…
Unveiling Privacy, Memorization, and Input Curvature Links
Deepak Ravikumar, Efstathia Soufleri, Abolfazl Hashemi +1
Deep Neural Nets (DNNs) have become a pervasive tool for solving many emerging problems. However, they tend to overfit to and memorize the training set. Memorization is of keen int…