Follow
Sidak Pal Singh
Sidak Pal Singh
ETH Zurich, Max Planck Institute for Intelligent Systems
Verified email at inf.ethz.ch - Homepage
Title
Cited by
Cited by
Year
Model Fusion via Optimal Transport
SP Singh, M Jaggi
NeurIPS 2020, 2019
2412019
Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning
E Frantar, SP Singh, D Alistarh
NeurIPS 2022, 2022
2222022
WoodFisher: Efficient Second-Order Approximation for Neural Network Compression
SP Singh, D Alistarh
NeurIPS 2020, 2020
1952020
Signal Propagation in Transformers: Theoretical Perspectives and the Role of Rank Collapse
L Noci, S Anagnostidis, L Biggio, A Orvieto, SP Singh, A Lucchi
NeurIPS 2022, 2022
752022
Analytic Insights into Structure and Rank of Neural Network Hessian Maps
SP Singh, G Bachmann, T Hofmann
NeurIPS 2021, 2021
362021
Context Mover's Distance & Barycenters: Optimal transport of contexts for building representations
SP Singh, A Hug, A Dieuleveut, M Jaggi
AISTATS 2020 and ICLR 2019 Workshop on Deep Generative Models, 2018
362018
Some Fundamental Aspects about Lipschitz Continuity of Neural Network Functions
G Khromov, SP Singh
ICLR 2024, 2023
22*2023
Transformer Fusion with Optimal Transport
M Imfeld, J Graldi, M Giordano, T Hofmann, S Anagnostidis, SP Singh
ICLR 2024, 2023
192023
Rethinking Attention: Exploring Shallow Feed-Forward Neural Networks as an Alternative to Attention Layers in Transformers (Student Abstract)
D Dordevic, V Bozic, J Thommes, D Coppola, SP Singh
Proceedings of the AAAI Conference on Artificial Intelligence 38 (21), 23477 …, 2024
16*2024
Phenomenology of Double Descent in Finite-Width Neural Networks
SP Singh, A Lucchi, T Hofmann, B Schölkopf
ICLR 2022, 2021
142021
The Hessian perspective into the Nature of Convolutional Neural Networks
SP Singh, T Hofmann, B Schölkopf
ICML 2023, 2023
72023
Towards Meta-Pruning via Optimal Transport
A Theus, O Geimer, F Wicke, T Hofmann, S Anagnostidis, SP Singh
ICLR 2024, 2024
52024
On the curvature of the loss landscape
A Pouplin, H Roy, SP Singh, G Arvanitidis
arXiv preprint arXiv:2307.04719, 2023
22023
GLOSS: Generative Latent Optimization of Sentence Representations
SP Singh, A Fan, M Auli
arXiv preprint arXiv:1907.06385, 2019
22019
What Does It Mean to Be a Transformer? Insights from a Theoretical Hessian Analysis
W Ormaniec, F Dangel, SP Singh
arXiv preprint arXiv:2410.10986, 2024
12024
Local vs Global continual learning
G Lanzillotta, SP Singh, BF Grewe, T Hofmann
arXiv preprint arXiv:2407.16611, 2024
12024
Closed form of the Hessian spectrum for some Neural Networks
SP Singh, T Hofmann
High-dimensional Learning Dynamics 2024: The Emergence of Structure and …, 2024
12024
Efficient second-order methods for model compression
SP Singh
Master Thesis, EPFL, 2020
12020
RaaS and Hierarchical Aggregation Revisited
R Ranchal, SP Singh, P Angin, A Mohindra, H Lei, B Bhargava
2017 IEEE International Conference on Web Services (ICWS), 41-48, 2017
12017
SL-FII: Syntactic and Lexical Constraints with Frequency based Iterative Improvement for Disease Mention Recognition in News Headlines
SP Singh, S Khosla, S Rustagi, M Patel, D Patel
BAI@ IJCAI, 2016
12016
The system can't perform the operation now. Try again later.
Articles 1–20