SPOC lab
- 29 followers
- Switzerland
- https://www.epfl.ch/labs/spoc/
Popular repositories Loading
-
-
Rigorous-dynamical-mean-field-theory
Rigorous-dynamical-mean-field-theory PublicCode for "Rigorous dynamical mean field theory for stochastic gradient descent methods"
Python 4
-
gibbs-sampler-neural-networks
gibbs-sampler-neural-networks PublicGibbs sampler for neural network posteriors
-
bilinear-sequence-regression
bilinear-sequence-regression PublicCode for the paper "Bilinear Sequence Regression: Model for Learning from Long Sequences of High-dimensional Tokens"
-
rectangular_RIE
rectangular_RIE PublicCode for reproducing the results in "Optimal denoising of rotationally invariant rectangular matrices"
-
double_descent_uncertainty
double_descent_uncertainty PublicCompanion repository for the paper "On double-descent in uncertainty quantification in overparametrized models"
Repositories
- bilinear-sequence-regression Public
Code for the paper "Bilinear Sequence Regression: Model for Learning from Long Sequences of High-dimensional Tokens"
SPOC-group/bilinear-sequence-regression’s past year of commit activity - phys-231-exercises Public
SPOC-group/phys-231-exercises’s past year of commit activity - counting-attention Public
SPOC-group/counting-attention’s past year of commit activity - ExtensiveWidthQuadraticSamples Public
Code repository for the paper "Bayes-optimal learning of an extensive-width neural network from quadratically many samples"
SPOC-group/ExtensiveWidthQuadraticSamples’s past year of commit activity - quenches-sk Public
SPOC-group/quenches-sk’s past year of commit activity - fixed_points_graph_CA Public
SPOC-group/fixed_points_graph_CA’s past year of commit activity - OneStepGD_asymptotics Public
code for Asymptotics of feature learning in two-layer networks after one gradient-step
SPOC-group/OneStepGD_asymptotics’s past year of commit activity
People
This organization has no public members. You must be a member to see who’s a part of this organization.
Top languages
Loading…
Most used topics
Loading…