English
Related papers

Related papers: Convex Quantization Preserves Logconcavity

200 papers

Optimization algorithms and Monte Carlo sampling algorithms have provided the computational foundations for the rapid growth in applications of statistical machine learning in recent years. There is, however, limited theoretical…

Machine Learning · Statistics 2022-06-08 Yi-An Ma , Yuansi Chen , Chi Jin , Nicolas Flammarion , Michael I. Jordan

As machine learning-based prediction systems are increasingly used in high-stakes situations, it is important to understand how such predictive models will perform upon deployment. Distribution-free uncertainty quantification techniques…

Machine Learning · Computer Science 2025-06-12 Jake C. Snell , Thomas L. Griffiths

Motivated by reducing the computational and storage costs of LLMs, model compression and KV cache compression have attracted much attention from researchers. However, current methods predominantly emphasize maintaining the performance of…

Machine Learning · Computer Science 2025-02-26 Zhenheng Tang , Xiang Liu , Qian Wang , Peijie Dong , Bingsheng He , Xiaowen Chu , Bo Li

Sparse high dimensional graphical model selection is a topic of much interest in modern day statistics. A popular approach is to apply l1-penalties to either (1) parametric likelihoods, or, (2) regularized regression/pseudo-likelihoods,…

Methodology · Statistics 2022-02-04 Kshitij Khare , Sang-Yun Oh , Bala Rajaratnam

Safety and liveness are elementary concepts of computation, and the foundation of many verification paradigms. The safety-liveness classification of boolean properties characterizes whether a given property can be falsified by observing a…

Logic in Computer Science · Computer Science 2023-07-25 Thomas A. Henzinger , Nicolas Mazzocchi , N. Ege Saraç

Uncertainty quantification is a key pillar of trustworthy machine learning. It enables safe reactions under unsafe inputs, like predicting only when the machine learning model detects sufficient evidence, discarding anomalous data, or…

Machine Learning · Computer Science 2024-08-27 Michael Kirchhof

A key task in Bayesian statistics is sampling from distributions that are only specified up to a partition function (i.e., constant of proportionality). However, without any assumptions, sampling (even approximately) can be #P-hard, and few…

Machine Learning · Computer Science 2018-12-03 Rong Ge , Holden Lee , Andrej Risteski

The false confidence theorem establishes that, for any data-driven, precise-probabilistic method for uncertainty quantification, there exists (non-trivial) false hypotheses to which the method tends to assign high confidence. This raises…

Statistics Theory · Mathematics 2024-04-26 Ryan Martin

For a sequence of nonnegative random variables, we provide simple necessary and sufficient conditions to ensure that each sequence of its forward convex combinations converges in probability to the same limit. These conditions correspond to…

Functional Analysis · Mathematics 2011-02-04 Constantinos Kardaras , Gordan Zitkovic

Stochastic convex optimization, where the objective is the expectation of a random convex function, is an important and widely used method with numerous applications in machine learning, statistics, operations research and other areas. We…

Machine Learning · Computer Science 2016-11-23 Vitaly Feldman , Cristobal Guzman , Santosh Vempala

Probability metrics constitute an important tool in probability theory and statistics \cite{DKS91}, \cite{R91}, \cite{Z83} as they are specific metrics on spaces of random variables which, by satisfying an extra condition, concord well with…

Probability · Mathematics 2015-11-19 Ben Berckmoes , Bob Lowen

Gibbs random fields play an important role in statistics, for example the autologistic model is commonly used to model the spatial distribution of binary variables defined on a lattice. However they are complicated to work with due to an…

Computation · Statistics 2012-07-25 Nial Friel

Likelihood methods for measuring statistical evidence obey the likelihood principle while maintaining bounded and well-controlled frequency properties. These methods lend themselves to sequential study designs because they measure the…

Methodology · Statistics 2017-11-07 Jeffrey D Blume , Leena Choi

Optimization is widely used in statistics, and often efficiently delivers point estimates on useful spaces involving structural constraints or combinatorial structure. To quantify uncertainty, Gibbs posterior exponentiates the negative loss…

Methodology · Statistics 2025-07-23 Cheng Zeng , Eleni Dilma , Jason Xu , Leo L Duan

Data analysis in HEP experiments often uses binned likelihood from data and finite Monte Carlo sample. Statistical uncertainty of Monte Carlo sample has been introduced in Frequentist Inference in some literatures, but they are not suitable…

High Energy Physics - Experiment · Physics 2023-09-28 Shilin Liu , Clark McGrew

Uncertainty is prevalent in engineering design, data-driven problems, and decision making broadly. Due to inherent risk-averseness and ambiguity about assumptions, it is common to address uncertainty by formulating and solving conservative…

Optimization and Control · Mathematics 2024-04-05 Johannes O. Royset

In this paper, we continue to study random convex analysis. First, we introduce the notion of an $L^0$--pre--barreled module. Then, we develop the theory of random duality under the framework of a random locally convex module endowed with…

Functional Analysis · Mathematics 2015-11-11 Tiexin Guo , Shien Zhao , Xiaolin Zeng

Sensitivity analysis is widely used to assess the robustness of causal conclusions in observational studies, yet its interaction with the structure of measured covariates is often overlooked. When latent confounders cannot be directly…

Methodology · Statistics 2026-02-17 Abhinandan Dalal , Iris Horng , Yang Feng , Dylan S. Small

Recently, based on the idea of randomizing space theory, random convex analysis has been being developed in order to deal with the corresponding problems in random environments such as analysis of conditional convex risk measures and the…

Functional Analysis · Mathematics 2017-09-11 Tiexin Guo , Erxin Zhang , Mingzhi Wu , Bixuan Yang , George Yuan , Xiaolin Zeng

A natural way of quantifying the ``amount of information'' in decision problems yields a globally concave value for information. Another (in contrast, adversarial) way almost never does.

Theoretical Economics · Economics 2024-04-02 Mark Whitmeyer