Muthu Chidambaram

Publication Activity (10 Years)

Years Active: 2021-2024
Publications (10 Years): 11

Top Topics

Learning Models

Manifold Structure

Scaling Factors

Top Venues

Publications

Muthu Chidambaram, Rong Ge
On the Limitations of Temperature Scaling for Distributions with Overlaps. ICLR (2024)
Muthu Chidambaram, Rong Ge
For Better or For Worse? Learning Minimum Variance Features With Label Augmentation. CoRR (2024)
Muthu Chidambaram, Rong Ge
Reassessing How to Compare and Improve the Calibration of Machine Learning Models. CoRR (2024)
Muthu Chidambaram, Holden Lee, Colin McSwiggen, Semon Rezchikov
How Flawed is ECE? An Analysis via Logit Smoothing. CoRR (2024)
Muthu Chidambaram, Chenwei Wu, Yu Cheng, Rong Ge
Hiding Data Helps: On the Benefits of Masking for Sparse Coding. CoRR (2023)
Muthu Chidambaram, Xiang Wang, Chenwei Wu, Rong Ge
Provably Learning Diverse Features in Multi-View Data with Midpoint Mixup. ICML (2023)
Muthu Chidambaram, Chenwei Wu, Yu Cheng, Rong Ge
Hiding Data Helps: On the Benefits of Masking for Sparse Coding. ICML (2023)
Muthu Chidambaram, Rong Ge
A Uniform Confidence Phenomenon in Deep Learning and its Implications for Calibration. CoRR (2023)
Muthu Chidambaram, Xiang Wang, Chenwei Wu, Rong Ge
Provably Learning Diverse Features in Multi-View Data with Midpoint Mixup. CoRR (2022)
Muthu Chidambaram, Xiang Wang, Yuzheng Hu, Chenwei Wu, Rong Ge
Towards Understanding the Data Dependency of Mixup-style Training. ICLR (2022)
Muthu Chidambaram, Xiang Wang, Yuzheng Hu, Chenwei Wu, Rong Ge
Towards Understanding the Data Dependency of Mixup-style Training. CoRR (2021)