English
Related papers

Related papers: Global Resolution: Optimal Multi-Draft Speculative…

200 papers

Prompt engineering plays a critical role in adapting large language models (LLMs) to complex reasoning and labeling tasks without the need for extensive fine-tuning. In this paper, we propose a novel prompt optimization pipeline for frame…

Computation and Language · Computer Science 2025-12-23 Do Minh Duc , Quan Xuan Truong , Nguyen Tat Dat , Nguyen Van Vinh

Speculative decoding generally dictates having a small, efficient draft model that is either pretrained or distilled offline to a particular target model series, for instance, Llama or Qwen models. However, within online deployment…

Optimal transport (OT) theory underlies many emerging machine learning (ML) methods nowadays solving a wide range of tasks such as generative modeling, transfer learning and information retrieval. These latter works, however, usually build…

Machine Learning · Statistics 2021-12-03 Quang Huy Tran , Hicham Janati , Ievgen Redko , Rémi Flamary , Nicolas Courty

In this work, we study contextual strongly convex simulation optimization and adopt an "optimize then predict" (OTP) approach for real-time decision making. In the offline stage, simulation optimization is conducted across a set of…

Machine Learning · Statistics 2025-12-29 Nifei Lin , Heng Luo , L. Jeff Hong

Speculative decoding (SD) accelerates LLM inference by verifying draft tokens in parallel. However, this method presents a critical trade-off: it improves throughput in low-load, memory-bound systems but degrades performance in high-load,…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-03-04 Rui Li , Zhaoning Zhang , Libo Zhang , Huaimin Wang , Xiang Fu , Zhiquan Lai

Inference-time scaling has emerged as a powerful technique for enhancing the reasoning performance of Large Language Models (LLMs). However, existing approaches often rely on heuristic strategies for parallel sampling, lacking a principled…

Machine Learning · Computer Science 2025-12-22 Youkang Wang , Jian Wang , Rubing Chen , Xiao-Yong Wei

Large language models (LLMs) have achieved remarkable success across diverse tasks, yet their inference processes are hindered by substantial time and energy demands due to single-token generation at each decoding step. While previous…

Computation and Language · Computer Science 2025-04-11 Zongyue Qin , Ziniu Hu , Zifan He , Neha Prakriya , Jason Cong , Yizhou Sun

Speculative decoding speeds up autoregressive generation in Large Language Models (LLMs) through a two-step procedure, where a lightweight draft model proposes tokens which the target model then verifies in a single forward pass. Although…

Machine Learning · Computer Science 2026-05-12 Anton Plaksin , Sergei Krutikov , Sergei Skvortsov , Alexander Samarin

Optimal transport (OT) finds a least cost transport plan between two probability distributions using a cost matrix defined on pairs of points. Unlike standard OT, which infers unstructured pointwise mappings, low-rank optimal transport…

Machine Learning · Computer Science 2026-03-05 Henri Schmidt , Peter Halmos , Ben Raphael

Self-speculative decoding (SSD) accelerates LLM inference by skipping layers to create an efficient draft model, yet existing methods often rely on static heuristics that ignore the dynamic computational overhead of attention in…

Machine Learning · Computer Science 2026-02-25 Seongjin Cha , Gyuwan Kim , Dongsu Han , Tao Yang , Insu Han

The current best practice for computing optimal transport (OT) is via entropy regularization and Sinkhorn iterations. This algorithm runs in quadratic time as it requires the full pairwise cost matrix, which is prohibitively expensive for…

Machine Learning · Computer Science 2022-04-06 Johannes Gasteiger , Marten Lienen , Stephan Günnemann

Optimal-Transport Distributionally Robust Optimization (OT-DRO) robustifies data-driven decision-making under uncertainty by capturing the sampling-induced statistical error via optimal transport ambiguity sets. The standard OT-DRO pipeline…

Optimization and Control · Mathematics 2025-09-17 Jonas Ohnemus , Marta Fochesato , Riccardo Zuliani , John Lygeros

This paper presents a novel two-step approach for the fundamental problem of learning an optimal map from one distribution to another. First, we learn an optimal transport (OT) plan, which can be thought as a one-to-many map between the two…

Inference latency stands as a critical bottleneck in the large-scale deployment of Large Language Models (LLMs). Speculative decoding methods have recently shown promise in accelerating inference without compromising the output…

Machine Learning · Computer Science 2025-10-31 Ruilin Wang , Huixia Li , Yuexiao Ma , Xiawu Zheng , Fei Chao , Xuefeng Xiao , Rongrong Ji

Speculative decoding (SD) accelerates language model inference by drafting tokens from a cheap proposal model and verifying them against an expensive target model via rejection sampling. Because rejection truncates the draft block at the…

Large language model (LLM) decoding involves generating a sequence of tokens based on a given context, where each token is predicted one at a time using the model's learned probabilities. The typical autoregressive decoding method requires…

Computation and Language · Computer Science 2024-08-20 Xukun Liu , Bowen Lei , Ruqi Zhang , Dongkuan Xu

Explicit chain-of-thought (CoT) reasoning substantially improves the reasoning ability of large language models (LLMs), but incurs high inference cost due to lengthy autoregressive traces. Existing latent reasoning methods offer a promising…

Computation and Language · Computer Science 2026-05-26 Hui Xie , Jie Liu , Ziyue Qiao , Joaquin Vanschore

The offset optimization problem seeks to coordinate and synchronize the timing of traffic signals throughout a network in order to enhance traffic flow and reduce stops and delays. Recently, offset optimization was formulated into a…

Optimization and Control · Mathematics 2020-04-28 Yi Ouyang , Richard Y. Zhang , Javad Lavaei , Pravin Varaiya

Speculative Decoding (SD) accelerates autoregressive large language model (LLM) inference by decoupling generation and verification. While recent methods improve draft quality by tightly coupling the drafter with the target model, the…

Machine Learning · Computer Science 2026-04-14 Jingwei Song , Xinyu Wang , Hanbin Wang , Xiaoxuan Lei , Bill Shi , Shixin Han , Eric Yang , Xiao-Wen Chang , Lynn Ai

Over the past few years, numerous computational models have been developed to solve Optimal Transport (OT) in a stochastic setting, where distributions are represented by samples and where the goal is to find the closest map to the ground…

Statistics Theory · Mathematics 2023-02-01 Adrien Vacher , François-Xavier Vialard