Berivan Isik
8 papers · 2022–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
๐ Interdisciplinary Bridge ๐งญ Keyword Pioneer ๐ Conference Polyglot (4) ๐ Cross-Pollinator (11) ๐ Renaissance Researcher (5)
๐บ๏ธ
Taxonomy Completionist
(15)
Conferences
AISTATS (2)
ICLR (2)
ICML (2)
NIPS (2)
Top co-authors
Research topics
Keywords
communication efficiency
(2)
model compression
(2)
information theory
(2)
neural network compression
(1)
conformal prediction
(1)
convergence analysis
(1)
communication complexity
(1)
distributed learning
(1)
deep learning
(1)
neural network optimization
(1)
kullback-leibler divergence
(1)
side information
(1)
model pruning
(1)
communication compression
(1)
randomized sketching
(1)
communication overhead
(1)
overparameterized model
(1)
compression ratio
(1)
distributed mean estimation
(1)
rate-distortion theory
(1)
Papers
Scaling Laws for Downstream Task Performance in Machine Translation
ICLR 2025
Leveraging Per-Instance Privacy for Machine Unlearning
ICML 2025
Improved Communication-Privacy Trade-offs in $L_2$ Mean Estimation under Streaming Differential Privacy
ICML 2024
Adaptive Compression in Federated Learning via Side Information
AISTATS 2024
Sketching for Distributed Deep Learning: A Sharper Analysis
NIPS 2024
Sparse Random Networks for Communication-Efficient Federated Learning
ICLR 2023
Exact Optimality of Communication-Privacy-Utility Tradeoffs in Distributed Mean Estimation
NIPS 2023
An Information-Theoretic Justification for Model Pruning
AISTATS 2022