机器学习与统计学（MLSTAT）会议是由中国现场统计研究会机器学习分会主办的学术会议。会议旨在促进机器学习与统计领域的国内外学者进行学术交流，引领机器学习与统计共同交叉发展的学术文化，推动作为数据科学与人工智能的奠基性学科的进步，以此助力相关数字经济产业的发展。
第四届机器学习与统计学会议（MLSTAT2026）将于2026年7月15日-17日在西南财经大学（四川成都市）举行。会议将邀请20位左右青年学者就机器学习、人工智能、统计学和应用数学等相关领域的前沿进展做大会主题报告，同时欢迎在读博士生进行墙报展示。
主题：泛函尺度律：大模型尺度现象的动力学解释
报告人简介：吴磊，北京大学数学科学学院和国际机器学习研究中心助理教授，主要研究方向为深度学习的数理基础。2012年毕业于南开大学，获数学与应用数学学士学位；2018 年毕业于北京大学，获得计算数学博士学位。2018 年 11 月至 2021 年 10 月，先后在美国普林斯顿大学和宾夕法尼亚大学从事博士后研究工作。相关成果发表于 NeurIPS、ICML、Annals of Statistics、Journal of Machine Learning Research、 IEEE Transactions on Information Theory 等国际顶级会议与期刊。
报告摘要：大模型尺度律揭示：性能随训练数据规模和计算量的增长呈现出可预测的幂律提升。这一规律深刻推动了现代人工智能的发展，但长期停留在经验观察层面，缺乏理论理解。为探究其成因，我们引入幂律核回归（power-law kernel regression）这一简化模型，作为理论原型来抽象尺度现象的关键机制。基于该模型的动力学推导，我们提出泛函尺度律（Functional Scaling Laws, FSL）：通过"内蕴时间"这一核心概念，将尺度律扩展为刻画整个训练过程的"泛函"形式，从而统一描述了不同模型规模和超参数设置下的损失演化。更进一步，FSL还揭示了"预热-稳定-退火"等常用学习率调度策略的有效性，显示出对实际大模型训练的潜在指导价值。
主题：Approximating and learning smooth functions by ReLU neural networks
报告人简介：杨云斐，中山大学数学学院（珠海）副教授，2022年博士毕业于香港科技大学。研究兴趣包括机器学习、应用调和分析和逼近论。目前的研究工作主要集中于神经网络的逼近与泛化理论。相关研究成果发表于Journal of Machine Learning Research、Applied and Computational Harmonic Analysis、Constructive Approximation、NeurIPS等期刊和会议。
报告摘要：In this talk, we will discuss some recent progresses on the approximation and learning theory of ReLU neural networks. We divide the approximation theory of neural networks into two parts according to the methods. In the first method, we approximate smooth functions by piecewise polynomials and then construct neural networks to approximate these piecewise polynomials. Using constructive approximation, one can derive optimal approximation rates in terms of the width and depth. In the second method, we consider the function space of shallow neural networks, which is called Barron space, and use random approximation method to derive approximation bounds in this space. By studying the relation between the Barron space and the smooth function spaces, we can characterize the approximation error of shallow neural networks by the width and certain norm of the weights. As an application, we will discuss how these approximation results can be used in nonparametric regression problems. In particular, we will show that least squares estimations based on deep or shallow neural networks can achieve minimax optimal rates of convergence for learning smooth function classes in various settings.
主题：SpecTr-GBV: Multi-Draft Block Verification Accelerating Speculative Decoding
报告人简介：周峰，中国人民大学统计学院副教授，中国人民大学"杰出青年学者"，主要研究领域包括统计机器学习、贝叶斯方法、随机过程、大模型推理加速等，主持国家自然科学基金青年项目、面上项目，在JMLR、STCO、ICML、NeurIPS、ICLR、AAAI、KDD等国际期刊和会议上发表论文40余篇，担任NeurIPS、ICLR、AISTATS等国际会议领域主席，国际期刊《Statistics and Computing》副主编，《Transactions on Machine Learning Research》执行编辑，《Journal of Machine Learning Research》编委，中国商业统计学会人工智能分会副秘书长、全国工业统计学教学研究会青年统计学家协会第二届理事会理事、IEEE高级会员。
报告摘要：Autoregressive language models achieve state-of-the-art performance across a wide range of natural language processing tasks, but suffer from high inference latency due to their sequential decoding nature. Speculative decoding (SD) mitigates this by employing a lightweight draft model to propose candidate tokens, which are selectively verified by a larger target model. While existing methods either adopt multi-draft strategies to increase acceptance rates or block verification techniques to jointly verify multiple tokens, they remain limited by treating these improvements in isolation. In this work, we propose SpecTr-GBV, a novel SD method that unifies multi-draft and greedy block verification (GBV) into a single framework. By formulating the verification step as an optimal transport problem over draft and target token blocks, SpecTr-GBV improves both theoretical efficiency and empirical performance. We theoretically prove that SpecTr-GBV achieves the optimal expected number of accepted tokens for any fixed number of draft sequences, and this bound improves as the number of drafts increases. Empirically, we evaluate SpecTr-GBV across five datasets and four baselines. Our method achieves superior speedup and significantly higher block efficiency while preserving output quality. In addition, we perform comprehensive ablation studies to evaluate the impact of various hyperparameters in the model.
会议注册信息:
为了确保会议顺利开展，本次会议将少量收取注册费，会务组将承担会议期间的用餐，其他费用敬请自理！
注册费用：学生代表 200元，其他代表500元。
报名截止时间：2026年6月30日。
会议信息将通过本公众号及会议网站及时更新，欢迎大家积极关注。会议注册是通过会议网站注册。会议注册网址：
https://ml-stat.github.io/MLSTAT2026/register/
联系方式:
邮箱：mlstat2026@126.com
电话：028-87092330
