101 citations · 239 across the 36 of their papers we have counts for
42 papers
A Domain-Specific Harness for End-to-End Automation of Optimization Research
Heechang Kim, Ernest K. Ryu, Shuvomoy Das Gupta
We present AutoOPT, a domain-specific harness for end-to-end automation of optimization research. AutoOPT organizes the discovery of optimal first-order methods into four stages: n…
Censored Sampling of Diffusion Models Using 3 Minutes of Human Feedback
TaeHo Yoon, Kibeom Myoung, Keon Lee +3
Diffusion models have recently shown remarkable success in high-quality image generation. Sometimes, however, a pre-trained diffusion model exhibits partial misalignment in the sen…
Accelerating Value Iteration with Anchoring
Jongmin Lee, Ernest K. Ryu
Value Iteration (VI) is foundational to the theory and practice of modern reinforcement learning, and it is known to converge at a -rate, where is the discoun…
Computer-Assisted Design of Accelerated Composite Optimization Methods: OptISTA
Uijeong Jang, Shuvomoy Das Gupta, Ernest K. Ryu
The accelerated composite optimization method FISTA (Beck, Teboulle 2009) is suboptimal by a constant factor, and we present a new method OptISTA that improves FISTA by a constant…
Coordinate-Update Algorithms can Efficiently Detect Infeasible Optimization Problems
Jinhee Paeng, Jisun Park, Ernest K. Ryu
Coordinate update/descent algorithms are widely used in large-scale optimization due to their low per-iteration cost and scalability, but their behavior on infeasible or misspecifi…
Time-Reversed Dissipation Induces Duality Between Minimizing Gradient Norm and Function Value
Jaeyeon Kim, Asuman Ozdaglar, Chanwoo Park +1
In convex optimization, first-order optimization methods efficiently minimizing function values have been a central subject study since Nesterov's seminal work of 1983. Recently, h…