Skip to content
conftrace_

Nimit S Sohoni

3 papers · 2021–2022 · 1 venue · 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 ↓
🗺️ Taxonomy Completionist (11)

Venues

ICML (3)

Top co-authors

Christopher Re (3) Arjun Desai (1) Jessica Grogan (1) Mayee Chen (1) Chelsea Finn (1) Fait Poms (1) Kayvon Fatahalian (1) Michael Poli (1) Karan Goel (1) Alexander Liu (1)

Research topics

Machine Learning (3) Application Areas (3) Artificial Intelligence (2) Deep Learning (2) Core AI (1) Core Methods (1) Learning Paradigms (1) Learning Types · Machine Learning (1) Learning Types · Deep Learning (1) Techniques (1)

Keywords

model compression (1) structured matrix (1) representation learning (1) contrastive learning (1) domain generalization (1) domain adaptation (1) model evaluation (1) empirical risk minimization (1) matrix approximation (1) importance weighting (1) distribution shift (1) spurious correlation (1) representation alignment (1) sparse training (1) density ratio (1) worst-group generalization (1) neural network (1) worst-group robustness (1)

Papers

Correct-N-Contrast: a Contrastive Approach for Improving Robustness to Spurious Correlations ICML 2022 Monarch: Expressive Structured Matrices for Efficient and Accurate Training ICML 2022 Mandoline: Model Evaluation under Distribution Shift ICML 2021