collaborators

6 papers

cs.AI2026

AI-Assisted Discovery of Convex Relaxations via Dual Agents

Sungyoon Kim, Mert Pilanci

Recent work shows that LLM agents can improve sharp-constant inequalities by searching for extremal constructions, which yield upper bounds. We address the complementary side: a lo…

cs.AI2026

Optimizer-Induced Mode Connectivity: From AdamW to Muon

Fangzhao Zhang, Sungyoon Kim, Erica Zhang +2

Mode connectivity has been widely studied, yet the role of the optimizer remains underexplored. We revisit it through optimizer-induced implicit regularization, asking how connecti…

cs.IT2026

Optimal Scalar Quantization for Matrix Multiplication: Closed-Form Density and Phase Transition

Calvin Ang, Sungyoon Kim, Mert Pilanci

We study entrywise scalar quantization of two matrices prior to multiplication. Given and , we quantize entries of and independentl…

cs.DC2026

FlashSketch: Sketch-Kernel Co-Design for Fast Sparse Sketching on GPUs

Rajat Vadiraj Dwaraknath, Sungyoon Kim, Mert Pilanci

Sparse sketches such as the sparse Johnson-Lindenstrauss transform are a core primitive in randomized numerical linear algebra because they leverage random sparsity to reduce the a…

cs.LG2025

MatRL: Provably Generalizable Iterative Algorithm Discovery via Monte-Carlo Tree Search

Sungyoon Kim, Rajat Vadiraj Dwaraknath, Longling geng +1

Iterative methods for computing matrix functions have been extensively studied and their convergence speed can be significantly improved with the right tuning of parameters and by…

cs.LG2025

Exploring the loss landscape of regularized neural networks via convex duality

Sungyoon Kim, Aaron Mishkin, Mert Pilanci

We discuss several aspects of the loss landscape of regularized neural networks: the structure of stationary points, connectivity of optimal solutions, path with nonincreasing loss…