English
Related papers

Related papers: Variational Inference with Tail-adaptive f-Diverge…

200 papers

We develop a method to combine Markov chain Monte Carlo (MCMC) and variational inference (VI), leveraging the advantages of both inference approaches. Specifically, we improve the variational distribution by running a few MCMC steps. To…

Machine Learning · Statistics 2019-05-29 Francisco J. R. Ruiz , Michalis K. Titsias

We establish exponential inequalities and Cramer-type moderate deviation theorems for a class of V-statistics under strong mixing conditions. Our theory is developed via kernel expansion based on random Fourier features. This type of…

Statistics Theory · Mathematics 2019-02-08 Yandi Shen , Fang Han , Daniela Witten

We consider the problem of efficient simulation estimation of the density function at the tails, and the probability of large deviations for a sum of independent, identically distributed, light-tailed and non-lattice random vectors. The…

Probability · Mathematics 2017-04-26 Santanu Dey , Sandeep Juneja , Ankush Agarwal

As an emerging topic in face recognition, designing margin-based loss functions can increase the feature margin between different classes for enhanced discriminability. More recently, the idea of mining-based strategies is adopted to…

Computer Vision and Pattern Recognition · Computer Science 2020-04-02 Yuge Huang , Yuhan Wang , Ying Tai , Xiaoming Liu , Pengcheng Shen , Shaoxin Li , Jilin Li , Feiyue Huang

Stochastic volatility processes with heavy-tailed innovations are a well-known model for financial time series. In these models, the extremes of the log returns are mainly driven by the extremes of the i.i.d. innovation sequence which leads…

Probability · Mathematics 2016-03-25 Anja Janssen , Holger Drees

This paper provides a detailed investigation of using the Kullback-Leibler (KL) Divergence as a way to compare and analyse game-levels, and hence to use the measure as the objective function of an evolutionary algorithm to evolve new…

Neural and Evolutionary Computing · Computer Science 2019-05-14 Simon M. Lucas , Vanessa Volz

In few-shot learning, typically, the loss function which is applied at test time is the one we are ultimately interested in minimising, such as the mean-squared-error loss for a regression problem. However, given that we have few samples at…

Machine Learning · Computer Science 2019-12-02 Leo Feng , Luisa Zintgraf , Bei Peng , Shimon Whiteson

We introduce a class of variational actor-critic algorithms based on a variational formulation over both the value function and the policy. The objective function of the variational formulation consists of two parts: one for maximizing the…

Machine Learning · Computer Science 2023-01-18 Yuhua Zhu , Lexing Ying

Variational inference has recently emerged as a popular alternative to the classical Markov chain Monte Carlo (MCMC) in large-scale Bayesian inference. The core idea is to trade statistical accuracy for computational efficiency. In this…

Machine Learning · Statistics 2023-08-08 Kush Bhatia , Nikki Lijing Kuang , Yi-An Ma , Yixin Wang

We study in this paper the problem of least absolute deviation (LAD) regression for high-dimensional heavy-tailed time series which have finite $\alpha$-th moment with $\alpha \in (1,2]$. To handle the heavy-tailed dependent data, we…

Statistics Theory · Mathematics 2024-11-11 Yu Wang , Guodong Li , Zhijie Xiao , Lihu Xu , Wenyang Zhang

Numerous capability and safety techniques of Large Language Models (LLMs), including RLHF, automated red-teaming, prompt engineering, and infilling, can be cast as sampling from an unnormalized target distribution defined by a given reward…

Machine Learning · Computer Science 2024-05-01 Stephen Zhao , Rob Brekelmans , Alireza Makhzani , Roger Grosse

We propose a new and interpretable class of high-dimensional tail dependence models based on latent linear factor structures. Specifically, extremal dependence of an observable vector is assumed to be driven by a lower-dimensional latent…

Methodology · Statistics 2026-02-27 Alexis Boulin , Axel Bücher

Meta learning is a promising paradigm in the era of large models and task distributional robustness has become an indispensable consideration in real-world scenarios. Recent advances have examined the effectiveness of tail task risk…

Machine Learning · Computer Science 2024-10-31 Yiqin Lv , Qi Wang , Dong Liang , Zheng Xie

This paper introduces a novel perspective about error in machine learning and proposes inverse feature learning (IFL) as a representation learning approach that learns a set of high-level features based on the representation of error for…

Machine Learning · Computer Science 2020-03-10 Behzad Ghazanfari , Fatemeh Afghah

Approximating complex probability densities is a core problem in modern statistics. In this paper, we introduce the concept of Variational Inference (VI), a popular method in machine learning that uses optimization techniques to estimate…

Machine Learning · Computer Science 2021-11-23 Ankush Ganguly , Samuel W. F. Earp

We derive PAC-Bayesian learning guarantees for heavy-tailed losses, and obtain a novel optimal Gibbs posterior which enjoys finite-sample excess risk bounds at logarithmic confidence. Our core technique itself makes use of PAC-Bayesian…

Machine Learning · Statistics 2019-12-19 Matthew J. Holland

While fat-tailed densities commonly arise as posterior and marginal distributions in robust models and scale mixtures, they present challenges when Gaussian-based variational inference fails to capture tail decay accurately. We first…

Machine Learning · Statistics 2022-05-18 Feynman Liang , Liam Hodgkinson , Michael W. Mahoney

In this paper we propose a class of randomized primal-dual methods to contend with large-scale saddle point problems defined by a convex-concave function $\mathcal{L}(\mathbf{x},y)\triangleq\sum_{i=1}^m f_i(x_i)+\Phi(\mathbf{x},y)-h(y)$. We…

Optimization and Control · Mathematics 2023-03-17 E. Yazdandoost Hamedani , A. Jalilzadeh , N. S. Aybat

We introduce a deterministic variational formulation for training Bayesian last layer neural networks. This yields a sampling-free, single-pass model and loss that effectively improves uncertainty estimation. Our variational Bayesian last…

Machine Learning · Computer Science 2024-04-18 James Harrison , John Willes , Jasper Snoek

As a computational alternative to Markov chain Monte Carlo approaches, variational inference (VI) is becoming more and more popular for approximating intractable posterior distributions in large-scale Bayesian models due to its comparable…

Machine Learning · Statistics 2023-06-05 Anirban Bhattacharya , Debdeep Pati , Yun Yang