Publications

Train for the Worst, Plan for the Best: Understanding Token Ordering in Masked Diffusions
In recent years, masked diffusion models (MDMs) have emerged as a promising alternative approach for generative modeling over discrete …
Jaeyeon Kim, Kulin Shah*, Vasilis Kontonis, Sham Kakade, Sitan Chen
PDF
LoRA Training Provably Converges to a Low-Rank Global Minimum or It Fails Loudly (But it Probably Won't Fail)
Low-rank adaptation (LoRA) .
Junsu Kim, Jaeyeon Kim, Ernest K. Ryu
PDF
Task Diversity Shortens the ICL Plateau
In-context learning (ICL) describes a language model’s ability to generate outputs based on a set of input demonstrations and a …
Jaeyeon Kim, Sehyun Kwon*, Joo Young Choi, Jongho Park, Jaewoong Cho, Jason D. Lee, Ernest K. Ryu
PDF Cite
Optimal Acceleration for Minimax and Fixed-Point Problems is Not Unique
Recently, accelerated algorithms using the anchoring mechanism for minimax optimization and fixed-point problems have been proposed, …
TaeHo Yoon, Jaeyeon Kim, Jaewook J. Suh, Ernest K. Ryu
PDF Cite
Mirror Duality in Convex Optimization
While first-order optimization methods are usually designed to efficiently reduce the function value f(x), there has been recent …
Jaeyeon Kim, Chanwoo Park, Asuman Ozdaglar, Jelena Diakonikolas, Ernest K. Ryu
PDF Cite
Time-Reversed Dissipation Induces Duality Between Minimizing Gradient Norm and Function Value
In convex optimization, first-order optimization methods efficiently minimizing function values have been a central subject study since …
Jaeyeon Kim, Asuman Ozdaglar, Chanwoo Park, Ernest K. Ryu
PDF Cite