conftrace_

Chiraag Kaushik

3 papers · 2024–2024 · 3 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 🗺️ Taxonomy Completionist (10)

Venues

ICML (1) JMLR (1) NeurIPS (1)

Top co-authors

Vidya Muthukumar (3) Chi-Heng Lin (2) Matthew Y Jin (1) Amrit Khera (1) Eva L Dyer (1) Justin Romberg (1) Ran Liu (1) Eva L. Dyer (1) Wenrui Ma (1)

Research topics

Deep Learning (3) Machine Learning (3) Optimization & Theory · Machine Learning (3) Application Areas (1) Architectures (1) Core Methods (1) Learning Types · Deep Learning (1) Learning Types · Machine Learning (1) Optimization & Theory · Deep Learning (1)

Keywords

data augmentation (2) ridge regression (1) asymptotic analysis (1) spectral regularization (1) alternating minimization (1) linear neural network (1) overparameterized model (1) linear model (1) pretrained encoder (1) reweighted least square (1) bias (1) class disparity (1) high-dimensional mixture model (1) sparse recovery (1) spectral imbalance (1)

Papers

Balanced Data, Imbalanced Spectra: Unveiling Class Disparities with Spectral Imbalance ICML 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