Muthu Chidambaram
9 papers · 2019–2025 · 4 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 ↓
🌍
Conference Polyglot · Bronze
🏃
Academic Marathon · Sprint
🗺️
Taxonomy Completionist
(17)
👑
Triple Crown
❓
The Questioner
(3)
Venues
Top co-authors
Research topics
Keywords
data augmentation
(4)
feature learning
(2)
empirical risk minimization
(2)
zero-shot learning
(1)
calibration
(1)
sparse coding
(1)
probabilistic modeling
(1)
conditional distribution
(1)
confidence calibration
(1)
masked training
(1)
theoretical analysis
(1)
label smoothing
(1)
logistic loss
(1)
bregman divergence
(1)
kernel regression
(1)
model calibration
(1)
image classification
(1)
score estimation
(1)
semantic similarity
(1)
representation learning
(1)
Papers
For Better or For Worse? Learning Minimum Variance Features With Label Augmentation
ICLR 2025
Reassessing How to Compare and Improve the Calibration of Machine Learning Models
ICLR 2025
How Flawed Is ECE? An Analysis via Logit Smoothing
ICML 2024
On the Limitations of Temperature Scaling for Distributions with Overlaps
ICLR 2024
What does guidance do? A fine-grained analysis in a simple setting
NeurIPS 2024
Hiding Data Helps: On the Benefits of Masking for Sparse Coding
ICML 2023
Provably Learning Diverse Features in Multi-View Data with Midpoint Mixup
ICML 2023
Towards Understanding the Data Dependency of Mixup-style Training
ICLR 2022
Learning Cross-Lingual Sentence Representations via a Multi-task Dual-Encoder Model
ACL 2019