English
Related papers

Related papers: Gaussian Mixture Reduction Using Reverse Kullback-…

200 papers

Knowledge distillation (KD) is widely used for compressing a teacher model to a smaller student model, reducing its inference cost and memory footprint while preserving model capabilities. However, current KD methods for auto-regressive…

Computation and Language · Computer Science 2024-07-04 Jongwoo Ko , Sungnyun Kim , Tianyi Chen , Se-Young Yun

We propose an algorithm to estimate the path-gradient of both the reverse and forward Kullback-Leibler divergence for an arbitrary manifestly invertible normalizing flow. The resulting path-gradient estimators are straightforward to…

Machine Learning · Computer Science 2022-07-19 Lorenz Vaitl , Kim A. Nicoli , Shinichi Nakajima , Pan Kessel

In this paper, we study the statistical and geometrical properties of the Kullback-Leibler divergence with kernel covariance operators (KKL) introduced by Bach [2022]. Unlike the classical Kullback-Leibler (KL) divergence that involves…

Machine Learning · Statistics 2025-03-12 Clémentine Chazal , Anna Korba , Francis Bach

We investigate the use of alternative divergences to Kullback-Leibler (KL) in variational inference(VI), based on the Variational Dropout \cite{kingma2015}. Stochastic gradient variational Bayes (SGVB) \cite{aevb} is a general framework for…

Machine Learning · Statistics 2017-11-15 Bogdan Mazoure , Riashat Islam

We build a new class of generative algorithms capable of efficiently learning an arbitrary target distribution from possibly scarce, high-dimensional data and subsequently generate new samples. These generative algorithms are particle-based…

Machine Learning · Statistics 2024-08-29 Hyemin Gu , Panagiota Birmpa , Yannis Pantazis , Luc Rey-Bellet , Markos A. Katsoulakis

Robustness to outliers is a central issue in real-world machine learning applications. While replacing a model to a heavy-tailed one (e.g., from Gaussian to Student-t) is a standard approach for robustification, it can only be applied to…

Machine Learning · Statistics 2018-03-01 Futoshi Futami , Issei Sato , Masashi Sugiyama

Existing detection methods commonly use a parameterized bounding box (BBox) to model and detect (horizontal) objects and an additional rotation angle parameter is used for rotated objects. We argue that such a mechanism has fundamental…

Computer Vision and Pattern Recognition · Computer Science 2022-09-23 Xue Yang , Gefan Zhang , Xiaojiang Yang , Yue Zhou , Wentao Wang , Jin Tang , Tao He , Junchi Yan

We give a polynomial-time algorithm for the problem of robustly estimating a mixture of $k$ arbitrary Gaussians in $\mathbb{R}^d$, for any fixed $k$, in the presence of a constant fraction of arbitrary corruptions. This resolves the main…

Data Structures and Algorithms · Computer Science 2021-06-08 Ainesh Bakshi , Ilias Diakonikolas , He Jia , Daniel M. Kane , Pravesh K. Kothari , Santosh S. Vempala

Stein Variational Gradient Descent (SVGD), a popular sampling algorithm, is often described as the kernelized gradient flow for the Kullback-Leibler divergence in the geometry of optimal transport. We introduce a new perspective on SVGD…

Statistics Theory · Mathematics 2020-06-05 Sinho Chewi , Thibaut Le Gouic , Chen Lu , Tyler Maunu , Philippe Rigollet

The purpose of this paper is twofold. On a technical side, we propose an extension of the Hausdorff distance from metric spaces to spaces equipped with asymmetric distance measures. Specifically, we focus on the family of Bregman…

Machine Learning · Computer Science 2025-04-11 Tuyen Pham , Hana Dal Poz Kouřimská , Hubert Wagner

We propose a novel algorithm for unsupervised extraction of piecewise planar models from depth-data. Among other applications, such models are a good way of enabling autonomous agents (robots, cars, drones, etc.) to effectively perceive…

Computer Vision and Pattern Recognition · Computer Science 2022-09-29 Richard T. Marriott , Alexander Paschevich , Radu Horaud

Training Gaussian process-based models typically involves an $ O(N^3)$ computational bottleneck due to inverting the covariance matrix. Popular methods for overcoming this matrix inversion problem cannot adequately model all types of latent…

Machine Learning · Statistics 2020-03-04 Michael Minyi Zhang , Sinead A. Williamson

Large pretrained transformer models have revolutionized modern AI applications with their state-of-the-art performance in natural language processing (NLP). However, their substantial parameter count poses challenges for real-world…

Machine Learning · Statistics 2024-11-05 Mingxuan Zhang , Yan Sun , Faming Liang

We consider the problem of mixed linear regression (MLR), where each observed sample belongs to one of $K$ unknown linear models. In practical applications, the proportions of the $K$ components are often imbalanced. Unfortunately, most MLR…

Machine Learning · Statistics 2023-01-31 Pini Zilber , Boaz Nadler

We present 3DGS-LM, a new method that accelerates the reconstruction of 3D Gaussian Splatting (3DGS) by replacing its ADAM optimizer with a tailored Levenberg-Marquardt (LM). Existing methods reduce the optimization time by decreasing the…

Computer Vision and Pattern Recognition · Computer Science 2025-08-22 Lukas Höllein , Aljaž Božič , Michael Zollhöfer , Matthias Nießner

MAP inference for general energy functions remains a challenging problem. While most efforts are channeled towards improving the linear programming (LP) based relaxation, this work is motivated by the quadratic programming (QP) relaxation.…

Machine Learning · Computer Science 2012-06-22 Patrick Pletscher , Sharon Wulff

We revisit the challenging problem of training Gaussian-Bernoulli restricted Boltzmann machines (GRBMs), introducing two innovations. We propose a novel Gibbs-Langevin sampling algorithm that outperforms existing methods like Gibbs…

Machine Learning · Computer Science 2022-10-20 Renjie Liao , Simon Kornblith , Mengye Ren , David J. Fleet , Geoffrey Hinton

The state-of-the-art dimensionality reduction approaches largely rely on complicated optimization procedures. On the other hand, closed-form approaches requiring merely eigen-decomposition do not have enough sophistication and nonlinearity.…

Machine Learning · Computer Science 2023-08-14 Chengrui Li , Anqi Wu

Large language models (LLMs) have shown remarkable capabilities in language understanding and generation. However, such impressive capability typically comes with a substantial model size, which presents significant challenges in deployment…

Computation and Language · Computer Science 2025-06-26 Guinan Su , Li Shen , Lu Yin , Shiwei Liu , Yanwu Yang , Jonas Geiping

Generative models have achieved remarkable success across a range of applications, yet their evaluation still lacks principled uncertainty quantification. In this paper, we develop a method for comparing how close different generative…

Machine Learning · Statistics 2025-10-24 Zijun Gao , Yan Sun , Han Su
‹ Prev 1 4 5 6 7 8 10 Next ›