Blog Posts

[Ph.D. Thesis Proposal] Unraveling and Overcoming Challenges in Machine Learning: Generalizability, Adaptability, and Multifacetedness

👤 Hanseul Cho

🗓 January 24, 2025    

📌 Proposed for Ph.D. Candidacy Exam @ KAIST AI

[Paper Reading] Viewing Log-Depth Transformers via the Lens of Distributed Computing

🗓 October 10, 2024    

📌 Presented in OptiML Group Meeting (Fall 2024)

[Paper Reading] StableSSM: Alleviating the Curse of Memory in State-space Models through Stable Reparameterization

🗓 July 16, 2024    

📌 Presented in OptiML Group Meeting (Summer 2024)

[Paper Reading] Convex and Non-convex Optimization under Generalized Smoothness

🗓 June 03, 2024    

📌 Presented in AI709 Advanced Deep Learning Theory (Spring 2024)

[Paper Reading] Understanding Gradient Descent on Edge of Stability in Deep Learning

🗓 March 20, 2024    

📌 Presented in AI709 Advanced Deep Learning Theory (Spring 2024)

[Paper Reading] A U-turn on Double Descent: Rethinking Parameter Counting in Statistical Learning

🗓 March 07, 2024    

📌 Presented in OptiML Group Meeting (Spring 2024)

[Coursework Report] An Overview on Optimal Transport and its Application to Model Fusion

🗓 December 16, 2023    

📌 Final report for the coursework “Optimal Transport + Gradient Flow”

[Paper Reading] Implicit Bias of Large Depth Networks: a Notion of Rank for Nonlinear Functions

🗓 September 08, 2023    

📌 Presented in OptiML Group Meeting (Fall 2023)

[Paper Reading] Adversarial training descends without descent: Finding actual descent directions based on Danskin’s Theorem

🗓 March 17, 2023    

📌 Presented in OptiML Group Meeting (Spring 2023)

[Paper Reading] On Learning Fairness and Accuracy on Multiple Subgroups

🗓 January 04, 2023    

📌 Presented in OptiML Group Meeting (Spring 2023)

[Paper Reading] Offline Reinforcement Learning with Implicit Q Learning

🗓 November 28, 2022    

📌 Presented in AI611 Deep Reinforcement Learning (Fall 2022)

[Design] The Very First Draft of OptiML Lab’s Logo

🗓 November 28, 2022    

📌 Designed by myself (not knowing the first thing about artistic design)

[Paper Reading] WGAN with an Infinitely Wide Generator Has No Spurious Stationary Points

🗓 April 08, 2022    

📌 Presented in OptiML Group Meeting (Spring 2022)

[Paper Reading] [KR only] Are Transformers universal approximators of sequence-to-sequence functions?

🗓 January 30, 2022    

📌 Summary: The first paper quantified Transformer’s expressive power