38 citations · 247 across the 108 of their papers we have counts for
117 papers
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…
Convex Optimization for Alignment and Preference Learning on a Single GPU
Miria Feng, Mert Pilanci
Fine-tuning large language models (LLMs) to align with human preferences has driven the success of systems such as Gemini and ChatGPT. However, approaches like Reinforcement Learni…
Convex Low-resource Accent-Robust Language Detection in Speech Recognition
Miria Feng, William Tan, Mert Pilanci
Globalization and multiculturalism continue to produce increasingly diverse speech varieties. Yet current spoken dialogue systems frequently fail on under-represented dialects and…
Principled Design of Diffusion-based Optimizers for Inverse Problems
Julio Oscanoa, Irmak Sivgin, Cagan Alkan +4
Score-based diffusion models achieve state-of-the-art performance for inverse problems, but their practical deployment is hindered by long inference times and cumbersome hyperparam…
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…
Unveiling Hidden Convexity in Deep Learning: a Sparse Signal Processing Perspective
Emi Zeger, Mert Pilanci
Deep neural networks (DNNs), particularly those using Rectified Linear Unit (ReLU) activation functions, have achieved remarkable success across diverse machine learning tasks, inc…
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…
ASMIL: Attention-Stabilized Multiple Instance Learning for Whole Slide Imaging
Linfeng Ye, Shayan Mohajer Hamidi, Zhixiang Chi +5
Attention-based multiple instance learning (MIL) has emerged as a powerful framework for whole slide image (WSI) diagnosis, leveraging attention to aggregate instance-level feature…
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…
An Information-Theoretic Perspective on LLM Tokenizers
Mete Erdogan, Abhiram Gorle, Shubham Chandak +2
Large language model (LLM) tokenizers act as structured compressors: by mapping text to discrete token sequences, they determine token count (and thus compute and context usage) an…
Learning When to Trust LLM Priors: A Validated Framework for Semantic Prior Integration
Erica Zhang, Naomi Sagan, Danny Tse +3
Large language models (LLMs) encode rich semantic knowledge that can be useful for supervised learning, but their outputs are unreliable as statistical priors: they may be noisy, m…
Thinking While Listening: Simple Test Time Scaling For Audio Classification
Prateek Verma, Mert Pilanci
We propose a framework that enables neural models to "think while listening" to everyday sounds, thereby enhancing audio classification performance. Motivated by recent advances in…
A Recovery Guarantee for Sparse Neural Networks
Sara Fridovich-Keil, Mert Pilanci
We prove the first guarantees of sparse recovery for ReLU neural networks, where the sparse network weights constitute the signal to be recovered. Specifically, we study structural…
DRIVE: Dynamic Rule Inference and Verified Evaluation for Constraint-Aware Autonomous Driving
Longling Geng, Huangxing Li, Viktor Lado Naess +1
Understanding and adhering to soft constraints is essential for safe and socially compliant autonomous driving. However, such constraints are often implicit, context-dependent, and…
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…
Large Language Models Implicitly Learn to See and Hear Just By Reading
Prateek Verma, Mert Pilanci
This paper presents a fascinating find: By training an auto-regressive LLM model on text tokens, the text model inherently develops internally an ability to understand images and a…
Spectral-Aware Low-Rank Adaptation for Speaker Verification
Zhe Li, Man-wai Mak, Mert Pilanci +2
Previous research has shown that the principal singular vectors of a pre-trained model's weight matrices capture critical knowledge. In contrast, those associated with small singul…
LLM-Lasso: A Robust Framework for Domain-Informed Feature Selection and Regularization
Erica Zhang, Ryunosuke Goto, Naomi Sagan +7
We introduce LLM-Lasso, a novel framework that leverages large language models (LLMs) to guide feature selection in Lasso regression. Unlike traditional methods that rely…
Geometric Algebra Planes: Convex Implicit Neural Volumes
Irmak Sivgin, Sara Fridovich-Keil, Gordon Wetzstein +1
Volume parameterizations abound in recent literature, from the classic voxel grid to the implicit neural representation and everything in between. While implicit representations ha…
CRONOS: Enhancing Deep Learning with Scalable GPU Accelerated Convex Neural Networks
Miria Feng, Zachary Frangella, Mert Pilanci
We introduce the CRONOS algorithm for convex optimization of two-layer neural networks. CRONOS is the first algorithm capable of scaling to high-dimensional datasets such as ImageN…
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…
Black Boxes and Looking Glasses: Multilevel Symmetries, Reflection Planes, and Convex Optimization in Deep Networks
Emi Zeger, Mert Pilanci
We show that training deep neural networks (DNNs) with absolute value activation and arbitrary input dimension can be formulated as equivalent convex Lasso problems with novel feat…
Convex Distillation: Efficient Compression of Deep Networks via Convex Optimization
Prateek Varshney, Mert Pilanci
Deploying large and complex deep neural networks on resource-constrained edge devices poses significant challenges due to their computational demands and the complexities of non-co…
Newton Meets Marchenko-Pastur: Massively Parallel Second-Order Optimization with Hessian Sketching and Debiasing
Elad Romanov, Fangzhao Zhang, Mert Pilanci
Motivated by recent advances in serverless cloud computing, in particular the "function as a service" (FaaS) model, we consider the problem of minimizing a convex function in a mas…