Yasaman Bahri
8 papers · 2017–2025 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
π£ Hot Topic Early Bird π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Bronze πΊοΈ Taxonomy Completionist (16) π Conference Polyglot Β· Bronze
π₯
Mega-Team Β· Squad
π
Conference Pioneer
π
Trend Setter
Venues
Top co-authors
Research topics
Machine Learning
(7)
Optimization & Theory
(6)
Deep Learning
(3)
Architectures
(3)
Artificial Intelligence
(2)
Computer Vision
(1)
Mathematics & Optimization
(1)
Natural Language Processing
(1)
Analysis
(1)
Application Areas
(1)
Applications
(1)
Bayesian & Probabilistic
(1)
Core AI Β· Artificial Intelligence
(1)
Core AI Β· Computer Vision
(1)
Core Methods
(1)
Keywords
gaussian process
(3)
infinite width
(2)
neural network
(2)
bayesian inference
(2)
convolutional neural network
(2)
neural network optimization
(1)
neural network theory
(1)
monte carlo estimation
(1)
gradient descent
(1)
generalization error
(1)
random matrix theory
(1)
relu activation
(1)
hessian eigenvalue
(1)
positional encoding
(1)
regression task
(1)
kernel function
(1)
linear model
(1)
orthogonal transformation
(1)
critical point
(1)
dynamical isometry
(1)
Papers
CURIE: Evaluating LLMs on Multitask Scientific Long-Context Understanding and Reasoning
ICLR 2025
Infinite attention: NNGP and NTK for deep attention networks
ICML 2020
Bayesian Deep Convolutional Networks with Many Channels are Gaussian Processes
ICLR 2019
Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent
NeurIPS 2019
Deep Neural Networks as Gaussian Processes
ICLR 2018
Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural Networks
ICML 2018
Sensitivity and Generalization in Neural Networks: an Empirical Study
ICLR 2018
Geometry of Neural Network Loss Surfaces via Random Matrix Theory
ICML 2017