English
Related papers

Related papers: Estimating Gradients for Discrete Random Variables…

200 papers

Differentially private empirical risk minimization (DP-ERM) is a fundamental problem in private optimization. While the theory of DP-ERM is well-studied, as large-scale models become prevalent, traditional DP-ERM methods face new…

Machine Learning · Computer Science 2024-06-05 Yin Tat Lee , Daogao Liu , Zhou Lu

Given a random sample from a parametric model, we show how indirect inference estimators based on appropriate nonparametric density estimators (i.e., simulation-based minimum distance estimators) can be constructed that, under mild…

Statistics Theory · Mathematics 2011-01-10 Richard Nickl , Benedikt M. Pötscher

Variational approximations are increasingly based on gradient-based optimization of expectations estimated by sampling. Handling discrete latent variables is then challenging because the sampling process is not differentiable. Continuous…

Machine Learning · Computer Science 2021-02-09 Tomasz Kuśmierczyk , Arto Klami

Maximum Likelihood Estimators (MLE) has many good properties. For example, the asymptotic variance of MLE solution attains equality of the asymptotic Cram{\'e}r-Rao lower bound (efficiency bound), which is the minimum possible variance for…

Machine Learning · Statistics 2019-11-05 Song Liu , Takafumi Kanamori , Wittawat Jitkrittum , Yu Chen

We propose a new optimization framework for aleatoric uncertainty estimation in regression problems. Existing methods can quantify the error in the target estimation, but they tend to underestimate it. To obtain the predictive uncertainty…

Computer Vision and Pattern Recognition · Computer Science 2021-03-12 Takumi Kawashima , Qing Yu , Akari Asai , Daiki Ikami , Kiyoharu Aizawa

Uncertainty estimation is an essential step in the evaluation of the robustness for deep learning models in computer vision, especially when applied in risk-sensitive areas. However, most state-of-the-art deep learning models either fail to…

Computer Vision and Pattern Recognition · Computer Science 2022-01-12 Lu Mi , Hao Wang , Yonglong Tian , Hao He , Nir Shavit

In recent years, multicalibration has emerged as a desirable learning objective for ensuring that a predictor is calibrated across a rich collection of overlapping subpopulations. Existing approaches typically achieve multicalibration by…

Machine Learning · Computer Science 2025-05-26 Hongyi Henry Jin , Zijun Ding , Dung Daniel Ngo , Zhiwei Steven Wu

We propose a stochastic representation for a simple class of transport PDEs based on Ito representations. We detail an algorithm using an estimator stemming for the representation that, unlike regularization by noise estimators, is…

Probability · Mathematics 2019-04-30 Goncalo dos Reis , Greig Smith

Approximation of the value functions in value-based deep reinforcement learning induces overestimation bias, resulting in suboptimal policies. We show that when the reinforcement signals received by the agents have a high variance, deep…

Machine Learning · Computer Science 2022-05-20 Baturay Saglam , Furkan Burak Mutlu , Dogan Can Cicek , Suleyman Serdar Kozat

In this paper we study covariance estimation with missing data. We consider missing data mechanisms that can be independent of the data, or have a time varying dependency. Additionally, observed variables may have arbitrary (non uniform)…

Statistics Theory · Mathematics 2021-06-17 Eduardo Pavez , Antonio Ortega

In this paper we present a frequentist-Bayesian hybrid method for estimating covariances of unfolded distributions using pseudo-experiments. The method is compared with other covariance estimation methods using the unbiased Rao-Cramer bound…

Methodology · Statistics 2021-10-19 Pim Jordi Verschuuren

In this work we consider the unbiased estimation of expectations w.r.t.~probability measures that have non-negative Lebesgue density, and which are known point-wise up-to a normalizing constant. We focus upon developing an unbiased method…

Computation · Statistics 2023-08-17 Hamza Ruzayqat , Neil K. Chada , Ajay Jasra

Risk minimization for nonsmooth nonconvex problems naturally leads to first-order sampling or, by an abuse of terminology, to stochastic subgradient descent. We establish the convergence of this method in the path-differentiable case and…

Optimization and Control · Mathematics 2024-07-24 Jérôme Bolte , Tam Le , Edouard Pauwels

Recent advances in large language models (LLMs) have shown that reasoning ability can be significantly enhanced through Reinforcement Learning with Verifiable Rewards (RLVR). Group Relative Policy Optimization (GRPO) has emerged as the de…

Computation and Language · Computer Science 2025-10-13 Jingyu Zhou , Lu Ma , Hao Liang , Chengyu Shen , Bin Cui , Wentao Zhang

Semiparametric discrete choice models are widely used in a variety of practical applications. While these models are point identified in the presence of continuous covariates, they can become partially identified when covariates are…

Econometrics · Economics 2024-05-29 Shakeeb Khan , Tatiana Komarova , Denis Nekipelov

Reparameterization (RP) and likelihood ratio (LR) gradient estimators are used throughout machine and reinforcement learning; however, they are usually explained as simple mathematical tricks without providing any insight into their nature.…

Machine Learning · Computer Science 2019-10-16 Paavo Parmas , Masashi Sugiyama

This paper proposes a differentiator for sampled signals with bounded noise and bounded second derivative. It is based on a linear program derived from the available sample information and requires no further tuning beyond the noise and…

Optimization and Control · Mathematics 2021-06-11 Hernan Haimovich , Richard Seeber , Rodrigo Aldana-López , David Gómez-Gutiérrez

Generative models, like large language models, are becoming increasingly relevant in our daily lives, yet a theoretical framework to assess their generalization behavior and uncertainty does not exist. Particularly, the problem of…

Machine Learning · Computer Science 2024-07-11 Sebastian G. Gruber , Florian Buettner

This paper studies the design of an optimal privacyaware estimator of a public random variable based on noisy measurements which contain private information. The public random variable carries non-private information, however, its estimate…

Optimization and Control · Mathematics 2018-08-08 Ehsan Nekouei , Henrik Sandberg , Mikael Skoglund , Karl H. Johansson

Flexible variational distributions improve variational inference but are harder to optimize. In this work we present a control variate that is applicable for any reparameterizable distribution with known mean and covariance matrix, e.g.…

Machine Learning · Computer Science 2020-10-26 Tomas Geffner , Justin Domke