Ashish J Khisti
4 papers · 2022–2025 · 2 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
🌉
Interdisciplinary Bridge · Silver
Top co-authors
Research topics
Keywords
neural network training
(1)
optimal transport
(1)
distributed computing
(1)
importance sampling
(1)
distribution shift
(1)
gradient coding
(1)
straggler mitigation
(1)
speculative sampling
(1)
lossy compression
(1)
language model inference
(1)
graph compression
(1)
bits-back coding
(1)
pólya's urn
(1)
edge exchangeability
(1)
quasi-linear complexity
(1)
token generation
(1)
edge-exchangeable graph
(1)
one-shot compression
(1)
network dataset
(1)
entropy bottleneck
(1)
Papers
Multi-Draft Speculative Sampling: Canonical Decomposition and Theoretical Limits
ICLR 2025
One-Shot Compression of Large Edge-Exchangeable Graphs using Bits-Back Coding
ICML 2023
Sequential Gradient Coding For Straggler Mitigation
ICLR 2023
LOSSY COMPRESSION WITH DISTRIBUTION SHIFT AS ENTROPY CONSTRAINED OPTIMAL TRANSPORT
ICLR 2022