Picture for Manfred K. Warmuth

Manfred K. Warmuth

Google Inc

Noise misleads rotation invariant algorithms on sparse targets

Add code
Mar 05, 2024
Figure 1 for Noise misleads rotation invariant algorithms on sparse targets
Figure 2 for Noise misleads rotation invariant algorithms on sparse targets
Figure 3 for Noise misleads rotation invariant algorithms on sparse targets
Figure 4 for Noise misleads rotation invariant algorithms on sparse targets
Viaarxiv icon

Tempered Calculus for ML: Application to Hyperbolic Model Embedding

Add code
Feb 08, 2024
Viaarxiv icon

The Tempered Hilbert Simplex Distance and Its Application To Non-linear Embeddings of TEMs

Add code
Nov 22, 2023
Viaarxiv icon

Optimal Transport with Tempered Exponential Measures

Add code
Sep 07, 2023
Figure 1 for Optimal Transport with Tempered Exponential Measures
Figure 2 for Optimal Transport with Tempered Exponential Measures
Figure 3 for Optimal Transport with Tempered Exponential Measures
Figure 4 for Optimal Transport with Tempered Exponential Measures
Viaarxiv icon

Boosting with Tempered Exponential Measures

Add code
Jun 08, 2023
Figure 1 for Boosting with Tempered Exponential Measures
Figure 2 for Boosting with Tempered Exponential Measures
Figure 3 for Boosting with Tempered Exponential Measures
Figure 4 for Boosting with Tempered Exponential Measures
Viaarxiv icon

A Mechanism for Sample-Efficient In-Context Learning for Sparse Retrieval Tasks

Add code
May 26, 2023
Figure 1 for A Mechanism for Sample-Efficient In-Context Learning for Sparse Retrieval Tasks
Figure 2 for A Mechanism for Sample-Efficient In-Context Learning for Sparse Retrieval Tasks
Figure 3 for A Mechanism for Sample-Efficient In-Context Learning for Sparse Retrieval Tasks
Figure 4 for A Mechanism for Sample-Efficient In-Context Learning for Sparse Retrieval Tasks
Viaarxiv icon

Layerwise Bregman Representation Learning with Applications to Knowledge Distillation

Add code
Sep 15, 2022
Figure 1 for Layerwise Bregman Representation Learning with Applications to Knowledge Distillation
Figure 2 for Layerwise Bregman Representation Learning with Applications to Knowledge Distillation
Figure 3 for Layerwise Bregman Representation Learning with Applications to Knowledge Distillation
Figure 4 for Layerwise Bregman Representation Learning with Applications to Knowledge Distillation
Viaarxiv icon

Learning from Randomly Initialized Neural Network Features

Add code
Feb 13, 2022
Figure 1 for Learning from Randomly Initialized Neural Network Features
Figure 2 for Learning from Randomly Initialized Neural Network Features
Figure 3 for Learning from Randomly Initialized Neural Network Features
Figure 4 for Learning from Randomly Initialized Neural Network Features
Viaarxiv icon

Step-size Adaptation Using Exponentiated Gradient Updates

Add code
Jan 31, 2022
Figure 1 for Step-size Adaptation Using Exponentiated Gradient Updates
Figure 2 for Step-size Adaptation Using Exponentiated Gradient Updates
Figure 3 for Step-size Adaptation Using Exponentiated Gradient Updates
Figure 4 for Step-size Adaptation Using Exponentiated Gradient Updates
Viaarxiv icon

LocoProp: Enhancing BackProp via Local Loss Optimization

Add code
Jun 11, 2021
Figure 1 for LocoProp: Enhancing BackProp via Local Loss Optimization
Figure 2 for LocoProp: Enhancing BackProp via Local Loss Optimization
Figure 3 for LocoProp: Enhancing BackProp via Local Loss Optimization
Figure 4 for LocoProp: Enhancing BackProp via Local Loss Optimization
Viaarxiv icon