Skip to content
conftrace_

Nikolaos Tsilivis

5 papers · 2022–2026 · 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 (20) ❓ The Questioner

Venues

NeurIPS (3) ICLR (1) JMLR (1)

Top co-authors

Julia Kempe (4) Gal Vardi (2) Natalie S. Frank (1) Ezra Edelman (1) Nathan Srebro (1) Surbhi Goel (1) Eitan Gronich (1) Eran Malach (1) Benjamin L. Edelman (1)

Research topics

Deep Learning (5) Machine Learning (5) Optimization & Theory · Machine Learning (4) Architectures (3) Learning Types · Machine Learning (3) Optimization & Theory · Deep Learning (3) Artificial Intelligence (2) Core AI (2) Core Methods (2) Learning Types · Deep Learning (2)

Keywords

implicit bia (3) margin maximization (2) steepest descent (2) neural network optimization (2) empirical risk minimization (1) gradient descent (1) markov chain (1) adaptive optimization (1) adversarial perturbation (1) language model (1) induction head (1) bigram statistics (1) next-token prediction (1) feature decomposition (1) adversarial example (1) robust generalization (1) robust erm (1) linear model (1) robust feature (1) kernel methods (1)

Papers

Flavors of Margin: Implicit Bias of Steepest Descent in Homogeneous Neural Networks JMLR 2026 Flavors of Margin: Implicit Bias of Steepest Descent in Homogeneous Neural Networks ICLR 2025 The Evolution of Statistical Induction Heads: In-Context Learning Markov Chains NeurIPS 2024 The Price of Implicit Bias in Adversarially Robust Generalization NeurIPS 2024 What Can the Neural Tangent Kernel Tell Us About Adversarial Robustness? NeurIPS 2022