Tyler Farghly
4 papers · 2020–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
๐งญ Keyword Pioneer ๐ Conference Polyglot (4) ๐ Academic Marathon (5) ๐ Cross-Pollinator (6) ๐ Renaissance Researcher (5)
๐
Interdisciplinary Bridge
๐บ๏ธ
Taxonomy Completionist
(10)
๐ฃ
Hot Topic Early Bird
Conferences
ACL (1)
ALT (1)
JMLR (1)
NIPS (1)
Top co-authors
Research topics
Keywords
few-shot learning
(1)
non-convex optimization
(1)
algorithmic stability
(1)
generalization bound
(1)
iteration complexity
(1)
wasserstein metric
(1)
stochastic gradient langevin dynamics
(1)
heavy-tailed sampling
(1)
langevin diffusion
(1)
ito diffusion
(1)
mean-square analysis
(1)
gaussian smoothing
(1)
span extraction
(1)
dialog system
(1)
stochastic sampling
(1)
conversational model
(1)
uniform stability
(1)
itรด diffusion
(1)
pretrained conversational model
(1)
wasserstein contraction
(1)
Papers
Generalisation under gradient descent via deterministic PAC-Bayes
ALT 2025
Mean-Square Analysis of Discretized Itรด Diffusions for Heavy-tailed Sampling
JMLR 2024
Time-independent Generalization Bounds for SGLD in Non-convex Settings
NIPS 2021
Span-ConveRT: Few-shot Span Extraction for Dialog with Pretrained Conversational Representations
ACL 2020