Boris Hanin
14 papers · 2018–2025 · 4 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 ↓+5 more ↓ Show less ↑
π£ Hot Topic Early Bird π Conference Polyglot Β· Bronze π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Bronze πΊοΈ Taxonomy Completionist (21)
π
Keyword Champion
(2)
ποΈ
Keyword Collector
(69)
π
Century Club Β· Bronze
π₯
Unstoppable Β· Bronze
β
The Questioner
(2)
Venues
Top co-authors
Research topics
Machine Learning
(14)
Optimization & Theory Β· Machine Learning
(12)
Deep Learning
(10)
Architectures
(8)
Optimization & Theory Β· Deep Learning
(6)
Artificial Intelligence
(2)
Mathematics & Optimization
(2)
Application Areas
(2)
Core AI
(2)
Learning Types
(2)
Mathematics
(1)
Models
(1)
Optimization
(1)
Techniques
(1)
Keywords
relu network
(5)
learning rate
(3)
neural network
(3)
neural network optimization
(2)
gradient descent
(2)
theoretical bound
(2)
vanishing gradient
(2)
relu activation
(2)
exploding gradient
(2)
residual network
(2)
preference learning
(1)
language model alignment
(1)
model safety
(1)
hyperparameter transfer
(1)
neural architecture search
(1)
hyperparameter optimization
(1)
neural network training
(1)
model architecture
(1)
convergence analysis
(1)
convex optimization
(1)
Papers
Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization
ICLR 2025
Are More LLM Calls All You Need? Towards the Scaling Properties of Compound AI Systems
NeurIPS 2024
Depthwise Hyperparameter Transfer in Residual Networks: Dynamics and Scaling Limit
ICLR 2024
Principled Architecture-aware Scaling of Hyperparameters
ICLR 2024
Random Fully Connected Neural Networks as Perturbatively Solvable Hierarchies
JMLR 2024
Maximal Initial Learning Rates in Deep ReLU Networks
ICML 2023
Deep Architecture Connectivity Matters for Its Convergence: A Fine-Grained Analysis
NeurIPS 2022
Deep ReLU Networks Preserve Expected Length
ICLR 2022
How Data Augmentation affects Optimization for Linear Regression
NeurIPS 2021
Finite Depth and Width Corrections to the Neural Tangent Kernel
ICLR 2020
Complexity of Linear Regions in Deep Networks
ICML 2019
Deep ReLU Networks Have Surprisingly Few Activation Patterns
NeurIPS 2019
How to Start Training: The Effect of Initialization and Architecture
NeurIPS 2018
Which Neural Net Architectures Give Rise to Exploding and Vanishing Gradients?
NeurIPS 2018