Alert button
Picture for Brando Miranda

Brando Miranda

Alert button

Is Pre-training Truly Better Than Meta-Learning?

Jun 24, 2023
Brando Miranda, Patrick Yu, Saumya Goyal, Yu-Xiong Wang, Sanmi Koyejo

Figure 1 for Is Pre-training Truly Better Than Meta-Learning?
Figure 2 for Is Pre-training Truly Better Than Meta-Learning?
Figure 3 for Is Pre-training Truly Better Than Meta-Learning?
Figure 4 for Is Pre-training Truly Better Than Meta-Learning?
Viaarxiv icon

Beyond Scale: the Diversity Coefficient as a Data Quality Metric Demonstrates LLMs are Pre-trained on Formally Diverse Data

Jun 24, 2023
Alycia Lee, Brando Miranda, Sanmi Koyejo

Figure 1 for Beyond Scale: the Diversity Coefficient as a Data Quality Metric Demonstrates LLMs are Pre-trained on Formally Diverse Data
Figure 2 for Beyond Scale: the Diversity Coefficient as a Data Quality Metric Demonstrates LLMs are Pre-trained on Formally Diverse Data
Figure 3 for Beyond Scale: the Diversity Coefficient as a Data Quality Metric Demonstrates LLMs are Pre-trained on Formally Diverse Data
Figure 4 for Beyond Scale: the Diversity Coefficient as a Data Quality Metric Demonstrates LLMs are Pre-trained on Formally Diverse Data
Viaarxiv icon

Are Emergent Abilities of Large Language Models a Mirage?

Apr 28, 2023
Rylan Schaeffer, Brando Miranda, Sanmi Koyejo

Figure 1 for Are Emergent Abilities of Large Language Models a Mirage?
Figure 2 for Are Emergent Abilities of Large Language Models a Mirage?
Figure 3 for Are Emergent Abilities of Large Language Models a Mirage?
Figure 4 for Are Emergent Abilities of Large Language Models a Mirage?
Viaarxiv icon

The Curse of Low Task Diversity: On the Failure of Transfer Learning to Outperform MAML and Their Empirical Equivalence

Aug 02, 2022
Brando Miranda, Patrick Yu, Yu-Xiong Wang, Sanmi Koyejo

Figure 1 for The Curse of Low Task Diversity: On the Failure of Transfer Learning to Outperform MAML and Their Empirical Equivalence
Figure 2 for The Curse of Low Task Diversity: On the Failure of Transfer Learning to Outperform MAML and Their Empirical Equivalence
Figure 3 for The Curse of Low Task Diversity: On the Failure of Transfer Learning to Outperform MAML and Their Empirical Equivalence
Figure 4 for The Curse of Low Task Diversity: On the Failure of Transfer Learning to Outperform MAML and Their Empirical Equivalence
Viaarxiv icon

Does MAML Only Work via Feature Re-use? A Data Centric Perspective

Dec 24, 2021
Brando Miranda, Yu-Xiong Wang, Sanmi Koyejo

Figure 1 for Does MAML Only Work via Feature Re-use? A Data Centric Perspective
Figure 2 for Does MAML Only Work via Feature Re-use? A Data Centric Perspective
Figure 3 for Does MAML Only Work via Feature Re-use? A Data Centric Perspective
Figure 4 for Does MAML Only Work via Feature Re-use? A Data Centric Perspective
Viaarxiv icon

The Curse of Zero Task Diversity: On the Failure of Transfer Learning to Outperform MAML and their Empirical Equivalence

Dec 24, 2021
Brando Miranda, Yu-Xiong Wang, Sanmi Koyejo

Figure 1 for The Curse of Zero Task Diversity: On the Failure of Transfer Learning to Outperform MAML and their Empirical Equivalence
Figure 2 for The Curse of Zero Task Diversity: On the Failure of Transfer Learning to Outperform MAML and their Empirical Equivalence
Figure 3 for The Curse of Zero Task Diversity: On the Failure of Transfer Learning to Outperform MAML and their Empirical Equivalence
Viaarxiv icon

Theory III: Dynamics and Generalization in Deep Networks - a simple solution

Apr 11, 2019
Andrzej Banburski, Qianli Liao, Brando Miranda, Lorenzo Rosasco, Bob Liang, Jack Hidary, Tomaso Poggio

Figure 1 for Theory III: Dynamics and Generalization in Deep Networks - a simple solution
Figure 2 for Theory III: Dynamics and Generalization in Deep Networks - a simple solution
Figure 3 for Theory III: Dynamics and Generalization in Deep Networks - a simple solution
Figure 4 for Theory III: Dynamics and Generalization in Deep Networks - a simple solution
Viaarxiv icon

A Surprising Linear Relationship Predicts Test Performance in Deep Networks

Jul 25, 2018
Qianli Liao, Brando Miranda, Andrzej Banburski, Jack Hidary, Tomaso Poggio

Figure 1 for A Surprising Linear Relationship Predicts Test Performance in Deep Networks
Figure 2 for A Surprising Linear Relationship Predicts Test Performance in Deep Networks
Figure 3 for A Surprising Linear Relationship Predicts Test Performance in Deep Networks
Figure 4 for A Surprising Linear Relationship Predicts Test Performance in Deep Networks
Viaarxiv icon

Theory IIIb: Generalization in Deep Networks

Jun 29, 2018
Tomaso Poggio, Qianli Liao, Brando Miranda, Andrzej Banburski, Xavier Boix, Jack Hidary

Figure 1 for Theory IIIb: Generalization in Deep Networks
Figure 2 for Theory IIIb: Generalization in Deep Networks
Figure 3 for Theory IIIb: Generalization in Deep Networks
Figure 4 for Theory IIIb: Generalization in Deep Networks
Viaarxiv icon

Theory of Deep Learning III: explaining the non-overfitting puzzle

Jan 16, 2018
Tomaso Poggio, Kenji Kawaguchi, Qianli Liao, Brando Miranda, Lorenzo Rosasco, Xavier Boix, Jack Hidary, Hrushikesh Mhaskar

Figure 1 for Theory of Deep Learning III: explaining the non-overfitting puzzle
Figure 2 for Theory of Deep Learning III: explaining the non-overfitting puzzle
Figure 3 for Theory of Deep Learning III: explaining the non-overfitting puzzle
Figure 4 for Theory of Deep Learning III: explaining the non-overfitting puzzle
Viaarxiv icon