Vidya Muthukumar
21 papers · 2019–2026 · 7 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (36) π Academic Marathon Β· Sprint π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Bronze π£ Hot Topic Early Bird
π
Keyword Champion
(2)
β‘
Prolific Year Β· Productive
π₯
Unstoppable Β· Bronze
β
The Questioner
(2)
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(90)
Top co-authors
Research topics
Machine Learning
(20)
Optimization & Theory Β· Machine Learning
(16)
Core Methods
(8)
Learning Types Β· Machine Learning
(7)
Mathematics & Optimization
(6)
Deep Learning
(5)
Optimization
(5)
Artificial Intelligence
(3)
Application Areas
(3)
Core AI
(3)
Learning Types Β· Deep Learning
(2)
Optimization & Theory Β· Deep Learning
(2)
Reinforcement Learning
(1)
Architectures
(1)
Learning Paradigms
(1)
Keywords
support vector machine
(3)
implicit bia
(3)
model selection
(2)
gradient descent
(2)
loss function
(2)
online learning
(2)
spurious correlation
(2)
multi-armed bandit
(2)
group robustness
(2)
data augmentation
(2)
regret bound
(2)
worst-group accuracy
(2)
inverse reinforcement learning
(1)
continuous optimization
(1)
sample complexity
(1)
ridge regression
(1)
reinforcement learning
(1)
function approximation
(1)
few-shot learning
(1)
asymptotic analysis
(1)
Papers
How Does the ReLU Activation Affect the Implicit Bias of Gradient Descent on High-dimensional Neural Network Regression?
COLT 2026
Last-iterate Convergence for Symmetric, General-sum, 2 Γ 2 Games Under The Exponential Weights Dynamic
ALT 2026
Estimating stationary mass, frequency by frequency
COLT 2025
General Loss Functions Lead to (Approximate) Interpolation in High Dimensions
JMLR 2025
Improved and Oracle-Efficient Online β_1-Multicalibration
ICML 2025
Task Shift: From Classification to Regression in Overparameterized Linear Models
AISTATS 2025
Balanced Data, Imbalanced Spectra: Unveiling Class Disparities with Spectral Imbalance
ICML 2024
Just Wing It: Near-Optimal Estimation of Missing Mass in a Markovian Sequence
JMLR 2024
One Shot Inverse Reinforcement Learning for Stochastic Linear Bandits
UAI 2024
Precise asymptotics of reweighted least-squares algorithms for linear diagonal networks
NeurIPS 2024
The good, the bad and the ugly sides of data augmentation: An implicit spectral regularization perspective
JMLR 2024
The Group Robustness is in the Details: Revisiting Finetuning under Spurious Correlations
NeurIPS 2024
Faster Margin Maximization Rates for Generic Optimization Methods
NeurIPS 2023
Towards Last-layer Retraining for Group Robustness with Fewer Annotations
NeurIPS 2023
Adaptive Oracle-Efficient Online Learning
NeurIPS 2022
Benign Overfitting in Multiclass Classification: All Roads Lead to Interpolation
NeurIPS 2021
Classification vs regression in overparameterized regimes: Does the loss function matter?
JMLR 2021
Online Model Selection for Reinforcement Learning with Function Approximation
AISTATS 2021
On the proliferation of support vectors in high dimensions
AISTATS 2021
OSOM: A simultaneously optimal algorithm for multi-armed and linear contextual bandits
AISTATS 2020
Best of many worlds: Robust model selection for online supervised learning
AISTATS 2019