Hanie Sedghi
14 papers · 2014–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
π Academic Marathon (11) π£ Hot Topic Early Bird π Interdisciplinary Bridge π Conference Polyglot (4) π Cross-Pollinator (11)
π
Cross-Pollinator
(11)
πΊοΈ
Taxonomy Completionist
(13)
π
Century Club
(14)
β
The Questioner
(2)
π
Trend Setter
π₯
Unstoppable
(5)
Conferences
ICLR (10)
NIPS (2)
AISTATS (1)
ICML (1)
Top co-authors
Keywords
stochastic optimization
(1)
matrix decomposition
(1)
transfer learning
(1)
parameter estimation
(1)
convergence analysis
(1)
loss landscape
(1)
minimax optimization
(1)
tensor decomposition
(1)
sparse optimization
(1)
high-dimensional optimization
(1)
alternating direction method
(1)
score function
(1)
mixture model
(1)
minimax rate
(1)
generalized linear model
(1)
alternating direction method of multiplier
(1)
feature reuse
(1)
pre-trained weight
(1)
neural network
(1)
Papers
Improving Large Language Model Planning with Action Sequence Similarity
ICLR 2025
REPAIR: REnormalizing Permuted Activations for Interpolation Repair
ICLR 2023
Can Neural Network Memorization Be Localized?
ICML 2023
Leveraging Unlabeled Data to Track Memorization
ICLR 2023
Leveraging unlabeled data to predict out-of-distribution performance
ICLR 2022
The Role of Permutation Invariance in Linear Mode Connectivity of Neural Networks
ICLR 2022
Exploring the Limits of Large Scale Pre-training
ICLR 2022
The Deep Bootstrap Framework: Good Online Learners are Good Offline Generalizers
ICLR 2021
What is being transferred in transfer learning?
NIPS 2020
The intriguing role of module criticality in the generalization of deep networks
ICLR 2020
Generalization bounds for deep convolutional neural networks
ICLR 2020
The Singular Values of Convolutional Layers
ICLR 2019
Provable Tensor Methods for Learning Mixtures of Generalized Linear Models
AISTATS 2016
Multi-Step Stochastic ADMM in High Dimensions: Applications to Sparse Optimization and Matrix Decomposition
NIPS 2014