Boris Hanin
14 papers · 2018–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
🏃 Academic Marathon (7) 🧭 Keyword Pioneer 🌉 Interdisciplinary Bridge 🌍 Conference Polyglot (4) 🐝 Cross-Pollinator (6)
🌍
Conference Polyglot
(4)
🏆
Keyword Champion
(2)
🧬
Topic Evolution
🗃️
Keyword Collector
(54)
💎
Century Club
(14)
🔥
Unstoppable
(8)
❓
The Questioner
(2)
Conferences
NIPS (6)
ICLR (5)
ICML (2)
JMLR (1)
Top co-authors
Keywords
relu network
(3)
exploding gradient
(2)
relu activation
(2)
residual network
(2)
gradient descent
(2)
vanishing gradient
(2)
learning rate
(2)
neural network
(2)
neural architecture search
(1)
gaussian process
(1)
convergence analysis
(1)
ensemble learning
(1)
piecewise linear function
(1)
perturbation theory
(1)
neural architecture
(1)
neural network optimization
(1)
data augmentation
(1)
random matrix theory
(1)
majority voting
(1)
network dynamics
(1)
Papers
Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization
ICLR 2025
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
Are More LLM Calls All You Need? Towards the Scaling Properties of Compound AI Systems
NIPS 2024
Maximal Initial Learning Rates in Deep ReLU Networks
ICML 2023
Deep ReLU Networks Preserve Expected Length
ICLR 2022
Deep Architecture Connectivity Matters for Its Convergence: A Fine-Grained Analysis
NIPS 2022
How Data Augmentation affects Optimization for Linear Regression
NIPS 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
NIPS 2019
Which Neural Net Architectures Give Rise to Exploding and Vanishing Gradients?
NIPS 2018
How to Start Training: The Effect of Initialization and Architecture
NIPS 2018