Micah Goldblum

When Do Neural Nets Outperform Boosted Trees on Tabular Data?

May 04, 2023
Duncan McElfresh, Sujay Khandagale, Jonathan Valverde, Vishak Prasad C, Ganesh Ramakrishnan, Micah Goldblum, Colin White

Access Paper or Ask Questions

A Cookbook of Self-Supervised Learning

Apr 24, 2023
Randall Balestriero, Mark Ibrahim, Vlad Sobal, Ari Morcos, Shashank Shekhar, Tom Goldstein, Florian Bordes, Adrien Bardes, Gregoire Mialon, Yuandong Tian, Avi Schwarzschild, Andrew Gordon Wilson, Jonas Geiping, Quentin Garrido, Pierre Fernandez, Amir Bar, Hamed Pirsiavash, Yann LeCun, Micah Goldblum

Figure 2 for A Cookbook of Self-Supervised Learning

Figure 3 for A Cookbook of Self-Supervised Learning

Figure 4 for A Cookbook of Self-Supervised Learning

Access Paper or Ask Questions

The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning

Apr 11, 2023
Micah Goldblum, Marc Finzi, Keefer Rowan, Andrew Gordon Wilson

Figure 2 for The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning

Figure 3 for The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning

Figure 4 for The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning

Access Paper or Ask Questions

Universal Guidance for Diffusion Models

Feb 14, 2023
Arpit Bansal, Hong-Min Chu, Avi Schwarzschild, Soumyadip Sengupta, Micah Goldblum, Jonas Geiping, Tom Goldstein

Figure 2 for Universal Guidance for Diffusion Models

Figure 3 for Universal Guidance for Diffusion Models

Figure 4 for Universal Guidance for Diffusion Models

Access Paper or Ask Questions

Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery

Feb 07, 2023
Yuxin Wen, Neel Jain, John Kirchenbauer, Micah Goldblum, Jonas Geiping, Tom Goldstein

Figure 2 for Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery

Figure 3 for Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery

Figure 4 for Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery

* 14 pages, 10 figures, Code is available at \url{https://github.com/YuxinWenRick/hard-prompts-made-easy}

Access Paper or Ask Questions

Exploring and Exploiting Decision Boundary Dynamics for Adversarial Robustness

Feb 06, 2023
Yuancheng Xu, Yanchao Sun, Micah Goldblum, Tom Goldstein, Furong Huang

Figure 2 for Exploring and Exploiting Decision Boundary Dynamics for Adversarial Robustness

Figure 3 for Exploring and Exploiting Decision Boundary Dynamics for Adversarial Robustness

Figure 4 for Exploring and Exploiting Decision Boundary Dynamics for Adversarial Robustness

* Published at International Conference on Learning Representations (ICLR) 2023

Access Paper or Ask Questions

What do Vision Transformers Learn? A Visual Exploration

Dec 13, 2022
Amin Ghiasi, Hamid Kazemi, Eitan Borgnia, Steven Reich, Manli Shu, Micah Goldblum, Andrew Gordon Wilson, Tom Goldstein

Figure 2 for What do Vision Transformers Learn? A Visual Exploration

Figure 3 for What do Vision Transformers Learn? A Visual Exploration

Figure 4 for What do Vision Transformers Learn? A Visual Exploration

Access Paper or Ask Questions

Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models

Dec 12, 2022
Gowthami Somepalli, Vasu Singla, Micah Goldblum, Jonas Geiping, Tom Goldstein

Figure 2 for Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models

Figure 3 for Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models

Figure 4 for Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models

* Updated draft with the following changes (1) Clarified the LAION Aesthetics versions everywhere (2) Correction on which LAION Aesthetics version SD - 1.4 is finetuned on and updated figure 12 based on this (3) A section on possible causes of replication

Access Paper or Ask Questions

Chroma-VAE: Mitigating Shortcut Learning with Generative Classifiers

Nov 28, 2022
Wanqian Yang, Polina Kirichenko, Micah Goldblum, Andrew Gordon Wilson

Figure 2 for Chroma-VAE: Mitigating Shortcut Learning with Generative Classifiers

Figure 3 for Chroma-VAE: Mitigating Shortcut Learning with Generative Classifiers

Figure 4 for Chroma-VAE: Mitigating Shortcut Learning with Generative Classifiers

* Presented at the 36th Conference on Neural Information Processing Systems (NeurIPS 2022)

Access Paper or Ask Questions