Sidak Pal Singh
15 papers · 2020–2025 · 5 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 ↑
🌍 Conference Polyglot · Silver 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (21) 🏆 Grand Slam
🗃️
Keyword Collector
(61)
🔥
Unstoppable · Bronze
❓
The Questioner
⚡
Prolific Year · Productive
💎
Century Club · Bronze
Top co-authors
Research topics
Machine Learning
(15)
Optimization & Theory · Machine Learning
(11)
Deep Learning
(7)
Architectures
(6)
Application Areas
(5)
Artificial Intelligence
(3)
Core AI
(3)
Optimization & Theory · Deep Learning
(3)
Techniques
(3)
Natural Language Processing
(1)
Core Methods
(1)
Learning Types · Deep Learning
(1)
Learning Types · Machine Learning
(1)
Resources & Methods
(1)
Keywords
neural network optimization
(5)
neural network
(4)
optimal transport
(4)
double descent
(2)
model compression
(2)
model architecture
(2)
neural network compression
(2)
deep linear network
(2)
hessian matrix
(2)
layer normalization
(2)
second-order optimization
(2)
attention mechanism
(2)
knowledge distillation
(1)
knowledge transfer
(1)
image classification
(1)
representation learning
(1)
unsupervised learning
(1)
network architecture
(1)
self-attention mechanism
(1)
sharpness-aware minimization
(1)
Papers
Avoiding spurious sharpness minimization broadens applicability of SAM
ICML 2025
The Directionality of Optimization Trajectories in Neural Networks
ICLR 2025
What Does It Mean to Be a Transformer? Insights from a Theoretical Hessian Analysis
ICLR 2025
Rethinking Attention: Exploring Shallow Feed-Forward Neural Networks as an Alternative to Attention Layers in Transformers (Student Abstract)
AAAI 2024
Some Fundamental Aspects about Lipschitz Continuity of Neural Networks
ICLR 2024
Theoretical Characterisation of the Gauss Newton Conditioning in Neural Networks
NeurIPS 2024
Towards Meta-Pruning via Optimal Transport
ICLR 2024
Transformer Fusion with Optimal Transport
ICLR 2024
The Hessian perspective into the Nature of Convolutional Neural Networks
ICML 2023
Phenomenology of Double Descent in Finite-Width Neural Networks
ICLR 2022
Signal Propagation in Transformers: Theoretical Perspectives and the Role of Rank Collapse
NeurIPS 2022
Analytic Insights into Structure and Rank of Neural Network Hessian Maps
NeurIPS 2021
Context Mover’s Distance & Barycenters: Optimal Transport of Contexts for Building Representations
AISTATS 2020
Model Fusion via Optimal Transport
NeurIPS 2020
WoodFisher: Efficient Second-Order Approximation for Neural Network Compression
NeurIPS 2020