Sidak Pal Singh

Venues

Frequent coauthors

Papers

1. Avoiding spurious sharpness minimization broadens applicability of SAM
   ICML 2025 · Sidak Pal Singh
2. Generalized Linear Mode Connectivity for Transformers
   NeurIPS 2025 ·

   Alexander Theus

   DBLP profile ↗ORCID search ↗
3. The Directionality of Optimization Trajectories in Neural Networks
   ICLR 2025 · Sidak Pal Singh
4. What Does It Mean to Be a Transformer? Insights from a Theoretical Hessian Analysis
   ICLR 2025 ·

   Weronika Ormaniec

   DBLP profile ↗ORCID search ↗
5. Rethinking Attention: Exploring Shallow Feed-Forward Neural Networks as an Alternative to Attention Layers in Transformers (Student Abstract)
   AAAI 2024 ·

   Danilo Dordevic

   DBLP profile ↗ORCID search ↗
6. Some Fundamental Aspects about Lipschitz Continuity of Neural Networks
   ICLR 2024 ·

   Grigory Khromov

   DBLP profile ↗ORCID search ↗
7. Theoretical Characterisation of the Gauss Newton Conditioning in Neural Networks
   NeurIPS 2024 ·

   Jim Zhao

   DBLP profile ↗ORCID search ↗
8. Towards Meta-Pruning via Optimal Transport
   ICLR 2024 ·

   Alexander Theus

   DBLP profile ↗ORCID search ↗
9. Transformer Fusion with Optimal Transport
   ICLR 2024 ·

   Moritz Imfeld

   DBLP profile ↗ORCID search ↗