90 citations · 308 across the 22 of their papers we have counts for
26 papers
Class-attribute Priors: Adapting Optimization to Heterogeneity and Fairness Objective
Xuechen Zhang, Mingchen Li, Jiasi Chen +2
Modern classification problems exhibit heterogeneities across individual classes: Each class may have unique attributes, such as sample size, label quality, or predictability (easy…
Transformers as Support Vector Machines
Davoud Ataee Tarzanagh, Yingcong Li, Christos Thrampoulidis +1
Since its inception in "Attention Is All You Need", transformer architecture has led to revolutionary advancements in NLP. The attention layer within the transformer admits a seque…
On the Role of Attention in Prompt-tuning
Samet Oymak, Ankit Singh Rawat, Mahdi Soltanolkotabi +1
Prompt-tuning is an emerging strategy to adapt large language models (LLM) to downstream tasks by learning a (soft-)prompt parameter from data. Despite its success in LLMs, there i…
FedNest: Federated Bilevel, Minimax, and Compositional Optimization
Davoud Ataee Tarzanagh, Mingchen Li, Christos Thrampoulidis +1
Standard federated optimization methods successfully apply to stochastic problems with single-level structure. However, many contemporary ML problems -- including adversarial robus…
AutoBalance: Optimized Loss Functions for Imbalanced Data
Mingchen Li, Xuechen Zhang, Christos Thrampoulidis +2
Imbalanced datasets are commonplace in modern machine learning problems. The presence of under-represented classes or groups with sensitive attributes results in concerns about gen…
Label-Imbalanced and Group-Sensitive Classification under Overparameterization
Ganesh Ramachandra Kini, Orestis Paraskevas, Samet Oymak +1
The goal in label-imbalanced and group-sensitive classification is to optimize relevant metrics such as balanced error and equal opportunity. Classical methods, such as weighted cr…
Provable Benefits of Overparameterization in Model Compression: From Double Descent to Pruning Neural Networks
Xiangyu Chang, Yingcong Li, Samet Oymak +1
Deep networks are typically trained with many more parameters than the size of the training dataset. Recent empirical evidence indicates that the practice of overparameterization n…
Theoretical Insights Into Multiclass Classification: A High-dimensional Asymptotic View
Christos Thrampoulidis, Samet Oymak, Mahdi Soltanolkotabi
Contemporary machine learning applications often involve classification tasks with many classes. Despite their extensive use, a precise understanding of the statistical properties…
Exploring Weight Importance and Hessian Bias in Model Pruning
Mingchen Li, Yahya Sattar, Christos Thrampoulidis +1
Model pruning is an essential procedure for building compact and computationally-efficient machine learning models. A key feature of a good pruning algorithm is that it accurately…
The Generalized Lasso for Sub-gaussian Measurements with Dithered Quantization
Christos Thrampoulidis, Ankit Singh Rawat
In the problem of structured signal recovery from high-dimensional linear observations, it is commonly assumed that full-precision measurements are available. Under this assumption…
Symbol Error Rate Performance of Box-relaxation Decoders in Massive MIMO
Christos Thrampoulidis, Weiyu Xu, Babak Hassibi
The maximum-likelihood (ML) decoder for symbol detection in large multiple-input multiple-output wireless communication systems is typically computationally prohibitive. In this pa…
Exploiting Occlusion in Non-Line-of-Sight Active Imaging
Christos Thrampoulidis, Gal Shulkind, Feihu Xu +5
Active non-line-of-sight imaging systems are of growing interest for diverse applications. The most commonly proposed approaches to date rely on exploiting time-resolved measuremen…
Phaseless super-resolution in the continuous domain
Myung Cho, Christos Thrampoulidis, Weiyu Xu +1
Phaseless super-resolution refers to the problem of superresolving a signal from only its low-frequency Fourier magnitude measurements. In this paper, we consider the phaseless sup…
Improved Bounds on the Epidemic Threshold of Exact SIS Models on Complex Networks
Navid Azizan Ruhi, Christos Thrampoulidis, Babak Hassibi
The SIS (susceptible-infected-susceptible) epidemic model on an arbitrary network, without making approximations, is a -state Markov chain with a unique absorbing state (the a…
Near-Optimal Sample Complexity Bounds for Circulant Binary Embedding
Samet Oymak
Binary embedding is the problem of mapping points from a high-dimensional space to a Hamming cube in lower dimension while preserving pairwise distances. An efficient way to accomp…
Precise Error Analysis of Regularized M-estimators in High-dimensions
Christos Thrampoulidis, Ehsan Abbasi, Babak Hassibi
A popular approach for estimating an unknown signal from noisy, linear measurements is via solving a so called \emph{regularized M-estimator}, which minimizes a weighted combinatio…
BER Analysis of the box relaxation for BPSK Signal Recovery
Christos Thrampoulidis, Ehsan Abbasi, Weiyu Xu +1
We study the problem of recovering an -dimensional vector of (BPSK) signals from noise corrupted measurements . In…
The LASSO with Non-linear Measurements is Equivalent to One With Linear Measurements
Chrtistos Thrampoulidis, Ehsan Abbasi, Babak Hassibi
Consider estimating an unknown, but structured, signal from measurement , where the 's are the rows of a known measurement matrix , and,…
Isotropically Random Orthogonal Matrices: Performance of LASSO and Minimum Conic Singular Values
Christos Thrampoulidis, Babak Hassibi
Recently, the precise performance of the Generalized LASSO algorithm for recovering structured signals from compressed noisy measurements, obtained via i.i.d. Gaussian matrices, ha…
Asymptotically Exact Error Analysis for the Generalized -LASSO
Christos Thrampoulidis, Ashkan Panahi, Babak Hassibi
Given an unknown signal and linear noisy measurements , the generalized -LASSO…
Precise Error Analysis of the -LASSO
Christos Thrampoulidis, Ashkan Panahi, Daniel Guo +1
A classical problem that arises in numerous signal processing applications asks for the reconstruction of an unknown, -sparse signal from underdetermined, noisy, li…
The Gaussian min-max theorem in the Presence of Convexity
Christos Thrampoulidis, Samet Oymak, Babak Hassibi
Gaussian comparison theorems are useful tools in probability theory; they are essential ingredients in the classical proofs of many results in empirical processes and extreme value…
Simple Error Bounds for Regularized Noisy Linear Inverse Problems
Christos Thrampoulidis, Samet Oymak, Babak Hassibi
Consider estimating a structured signal from linear, underdetermined and noisy measurements , via solving a variant of…
Simple Bounds for Noisy Linear Inverse Problems with Exact Side Information
Samet Oymak, Christos Thrampoulidis, Babak Hassibi
This paper considers the linear inverse problem where we wish to estimate a structured signal from its corrupted observations. When the problem is ill-posed, it is natural to m…