Ehsan Amid
22 papers · 2015–2026 · 10 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+9 more ↓ Show less ↑
π Academic Marathon (10) π§ Keyword Pioneer π Interdisciplinary Bridge π Conference Polyglot (9) π Cross-Pollinator (12)
π
Conference Polyglot
(9)
π
Academic Marathon
(10)
πΊοΈ
Taxonomy Completionist
(39)
π€
Dynamic Duo
(12)
π
Grand Slam
π
Keyword Champion
(2)
π
Century Club
(21)
ποΈ
Keyword Collector
(82)
π₯
Unstoppable
(7)
Conferences
NIPS (5)
AISTATS (3)
ICLR (3)
AAAI (2)
ALT (2)
COLT (2)
ICML (2)
EACL (1)
INTERSPEECH (1)
UAI (1)
Top co-authors
Keywords
gradient descent
(4)
bregman divergence
(3)
tempered exponential measure
(3)
online learning
(3)
expectation maximization
(2)
metric learning
(2)
multiplicative update
(2)
temperature parameter
(2)
sparse target
(2)
mirror descent
(2)
k-means clustering
(1)
logistic regression
(1)
matrix factorization
(1)
embedding learning
(1)
neural network training
(1)
stochastic gradient descent
(1)
computer vision
(1)
instruction following
(1)
principal component analysis
(1)
multi-task learning
(1)
Papers
We Are What We Repeatedly Do: Improving Long Context Instruction Following
EACL 2026
How rotation invariant algorithms are fooled by noise on sparse targets
ALT 2025
Restructuring Vector Quantization with the Rotation Trick
ICLR 2025
Context-Aware Meta-Learning
ICLR 2024
Hyperbolic Embeddings of Supervised Models
NIPS 2024
Optimal Transport with Tempered Exponential Measures
AAAI 2024
Clustering above Exponential Families with Tempered Exponential Measures
AISTATS 2023
Open Problem: Learning sparse linear concepts by priming the features
COLT 2023
Distributionally Robust Post-hoc Classifiers under Prior Shifts
ICLR 2023
Boosting with Tempered Exponential Measures
NIPS 2023
LocoProp: Enhancing BackProp via Local Loss Optimization
AISTATS 2022
Public Data-Assisted Mirror Descent for Private Model Training
ICML 2022
Extracting Targeted Training Data from ASR Models, and How to Mitigate It
INTERSPEECH 2022
Efficiently Identifying Task Groupings for Multi-Task Learning
NIPS 2021
A case where a spindly two-layer linear network decisively outperforms any neural network with a fully connected input layer
ALT 2021
Reparameterizing Mirror Descent as Gradient Descent
NIPS 2020
Divergence-Based Motivation for Online EM and Combining Hidden Variable Models
UAI 2020
An Implicit Form of Krasulina's k-PCA Update without the Orthonormality Constraint
AAAI 2020
Winnowing with Gradient Descent
COLT 2020
Robust Bi-Tempered Logistic Loss Based on Bregman Divergences
NIPS 2019
Two-temperature logistic regression based on the Tsallis divergence
AISTATS 2019
Multiview Triplet Embedding: Learning Attributes in Multiple Maps
ICML 2015