Tyler Farghly

5 papers · 2020–2026 · 5 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 · Silver 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (13)

Venues

ACL (1) ALT (1) COLT (1) JMLR (1) NeurIPS (1)

Top co-authors

Patrick Rebeschini (2) Simon Vary (1) Krishnakumar Balasubramanian (1) Daniela Gerz (1) Murat A. Erdogdu (1) Ivan Vulić (1) Arnaud Doucet (1) Samuel Coope (1) Matthew Henderson (1) Eugenio Clerico (1)

Research topics

Machine Learning (4) Optimization & Theory (4) Mathematics & Optimization (2) Artificial Intelligence (1) Deep Learning (1) Natural Language Processing (1) Applications (1) Core AI (1) Learning Paradigms (1) Optimization (1) Probability (1) Statistics (1) Techniques (1)

Keywords

generalization bound (2) few-shot learning (1) non-convex optimization (1) gradient descent (1) algorithmic stability (1) excess risk bound (1) iteration complexity (1) wasserstein metric (1) stochastic gradient langevin dynamics (1) effective dimension (1) heavy-tailed sampling (1) langevin diffusion (1) ito diffusion (1) mean-square analysis (1) gaussian smoothing (1) span extraction (1) dialog system (1) generalisation bound (1) stochastic sampling (1) conversational model (1)

Papers

On-Average Stability of Multipass Preconditioned SGD and Effective Dimension COLT 2026 Generalisation under gradient descent via deterministic PAC-Bayes ALT 2025 Mean-Square Analysis of Discretized Itô Diffusions for Heavy-tailed Sampling JMLR 2024 Time-independent Generalization Bounds for SGLD in Non-convex Settings NeurIPS 2021 Span-ConveRT: Few-shot Span Extraction for Dialog with Pretrained Conversational Representations ACL 2020