Om Thakkar
13 papers · 2018–2024 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+9 more ↓ Show less ↑
π Cross-Pollinator (4) π Academic Marathon (6) π§ Keyword Pioneer π Conference Polyglot (6) π Renaissance Researcher (5)
π
Renaissance Researcher
(5)
π
Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(24)
π
Grand Slam
π
Keyword Champion
π
Century Club
(13)
ποΈ
Keyword Collector
(53)
π₯
Unstoppable
(5)
β
The Questioner
Conferences
NIPS (4)
ICML (3)
AISTATS (2)
INTERSPEECH (2)
AAAI (1)
ICLR (1)
Top co-authors
Research topics
Keywords
differential privacy
(8)
federated learning
(4)
stochastic gradient descent
(2)
private model training
(2)
gradient clipping
(2)
speech recognition
(1)
privacy-preserving learning
(1)
self-supervised learning
(1)
loss landscape
(1)
generalized linear model
(1)
automatic speech recognition
(1)
empirical risk minimization
(1)
vc dimension
(1)
statistical query
(1)
distributed training
(1)
pac learning
(1)
linear regression
(1)
mirror descent
(1)
distribution shift
(1)
sample complexity
(1)
Papers
Quantifying Unintended Memorization in BEST-RQ ASR Encoders
INTERSPEECH 2024
Efficiently Train ASR Models that Memorize Less and Perform Better with Per-core Clipping
INTERSPEECH 2024
Why Is Public Pretraining Necessary for Private Model Training?
ICML 2023
Measuring Forgetting of Memorized Training Examples
ICLR 2023
Public Data-Assisted Mirror Descent for Private Model Training
ICML 2022
The Role of Adaptive Optimizers for Honest Private Hyperparameter Selection
AAAI 2022
Evading the Curse of Dimensionality in Unconstrained Private GLMs
AISTATS 2021
Revealing and Protecting Labels in Distributed Training
NIPS 2021
Differentially Private Learning with Adaptive Clipping
NIPS 2021
Practical and Private (Deep) Learning Without Sampling or Shuffling
ICML 2021
Guaranteed Validity for Empirical Approaches to Adaptive Data Analysis
AISTATS 2020
Privacy Amplification via Random Check-Ins
NIPS 2020
Model-Agnostic Private Learning
NIPS 2018