Bobak Kiani
7 papers · 2019–2024 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
๐ Interdisciplinary Bridge ๐งญ Keyword Pioneer ๐ฃ Hot Topic Early Bird ๐ Conference Polyglot (3) ๐ Academic Marathon (5)
๐
Cross-Pollinator
(12)
๐บ๏ธ
Taxonomy Completionist
(18)
Conferences
ICML (3)
NIPS (3)
ICLR (1)
Top co-authors
Keywords
deep neural network
(2)
self-supervised learning
(2)
representation learning
(2)
gaussian process
(1)
expressive power
(1)
parameter projection
(1)
generalization bound
(1)
recurrent neural network
(1)
partial differential equation
(1)
relu activation
(1)
inductive bia
(1)
adversarial perturbation
(1)
neural solver
(1)
binary classifier
(1)
adversarial example
(1)
gradient projection
(1)
polynomial feature
(1)
deep network
(1)
infinite width
(1)
network width
(1)
Papers
On the hardness of learning under symmetries
ICLR 2024
Self-Supervised Learning with Lie Symmetries for Partial Differential Equations
NIPS 2023
The SSL Interplay: Augmentations, Inductive Bias, and Generalization
ICML 2023
Equivariant Polynomials for Graph Neural Networks
ICML 2023
projUNN: efficient method for training deep networks with unitary matrices
NIPS 2022
Adversarial Robustness Guarantees for Random Deep Neural Networks
ICML 2021
Random deep neural networks are biased towards simple functions
NIPS 2019