English
Related papers

Related papers: Kernel Deformed Exponential Families for Sparse Co…

200 papers

We introduce a class of auto-encoder neural networks tailored to data from the natural exponential family (e.g., count data). The architectures are inspired by the problem of learning the filters in a convolutional generative model with…

Machine Learning · Computer Science 2020-06-30 Bahareh Tolooshams , Andrew H. Song , Simona Temereanca , Demba Ba

Modern sequence modeling is dominated by two families: Transformers, whose self-attention can access arbitrary elements of the visible sequence, and structured state-space models, which propagate information through an explicit recurrent…

Machine Learning · Computer Science 2026-04-22 Liubomyr Horbatko

Disentangled representation learning strives to extract the intrinsic factors within observed data. Factorizing these representations in an unsupervised manner is notably challenging and usually requires tailored loss functions or specific…

Computer Vision and Pattern Recognition · Computer Science 2024-06-13 Tao Yang , Cuiling Lan , Yan Lu , Nanning zheng

Temporal causal representation learning is a powerful tool for uncovering complex patterns in observational studies, which are often represented as low-dimensional time series. However, in many real-world applications, data are…

Machine Learning · Computer Science 2025-07-21 Jianhong Chen , Meng Zhao , Mostafa Reisi Gahrooei , Xubo Yue

Attention-based neural networks have achieved state-of-the-art results on a wide range of tasks. Most such models use deterministic attention while stochastic attention is less explored due to the optimization difficulties or complicated…

Machine Learning · Computer Science 2021-06-10 Shujian Zhang , Xinjie Fan , Bo Chen , Mingyuan Zhou

It is shown that a consistent application of Bayesian updating from a prior probability density to a posterior using evidence in the form of expectation constraints leads to exactly the same results as the application of the maximum entropy…

Data Analysis, Statistics and Probability · Physics 2016-05-02 Sergio Davis

While self-attention has been instrumental in the success of Transformers, it can lead to over-concentration on a few tokens during training, resulting in suboptimal information flow. Enforcing doubly-stochastic constraints in attention…

Machine Learning · Computer Science 2025-07-15 Ashkan Shahbazi , Elaheh Akbari , Darian Salehi , Xinran Liu , Navid Naderializadeh , Soheil Kolouri

We propose a simple modification to the conventional attention mechanism applied by Transformers: Instead of quantifying pairwise query-key similarity with scaled dot-products, we quantify it with the logarithms of scaled dot-products of…

Machine Learning · Computer Science 2024-04-30 Franz A. Heinsen

Attention mechanisms have become ubiquitous in NLP. Recent architectures, notably the Transformer, learn powerful context-aware word representations through layered, multi-headed attention. The multiple heads learn diverse types of word…

Computation and Language · Computer Science 2019-09-09 Gonçalo M. Correia , Vlad Niculae , André F. T. Martins

We introduce Exponential Family Discriminant Analysis (EFDA), a unified generative framework that extends classical Linear Discriminant Analysis (LDA) beyond the Gaussian setting to any member of the exponential family. Under the assumption…

Machine Learning · Computer Science 2026-03-25 Anish Lakkapragada

Many applications in speech, robotics, finance, and biology deal with sequential data, where ordering matters and recurrent structures are common. However, this structure cannot be easily captured by standard kernel functions. To model such…

Machine Learning · Computer Science 2017-10-06 Maruan Al-Shedivat , Andrew Gordon Wilson , Yunus Saatchi , Zhiting Hu , Eric P. Xing

We give a complete classification of 1-dimensional exponential families $\mathcal{E}$ defined over a finite space $\Omega=\{x_{0}, ...,x_{n}\}$ whose Hessian scalar curvature is constant. We observe an interesting phenomenon: if…

Differential Geometry · Mathematics 2019-06-07 Mathieu Molitor

Transformer is a transformative framework that models sequential data and has achieved remarkable performance on a wide range of tasks, but with high computational and energy cost. To improve its efficiency, a popular choice is to compress…

Computer Vision and Pattern Recognition · Computer Science 2023-03-21 Jing Liu , Zizheng Pan , Haoyu He , Jianfei Cai , Bohan Zhuang

Beyond their origin in modeling many-body quantum systems, tensor networks have emerged as a promising class of models for solving machine learning problems, notably in unsupervised generative learning. While possessing many desirable…

Machine Learning · Computer Science 2024-07-26 Alex Meiburg , Jing Chen , Jacob Miller , Raphaëlle Tihon , Guillaume Rabusseau , Alejandro Perdomo-Ortiz

Deep Gaussian Processes learn probabilistic data representations for supervised learning by cascading multiple Gaussian Processes. While this model family promises flexible predictive distributions, exact inference is not tractable.…

Machine Learning · Statistics 2020-10-23 Jakob Lindinger , David Reeb , Christoph Lippert , Barbara Rakitsch

Deep kernel learning provides an elegant and principled framework for combining the structural properties of deep learning algorithms with the flexibility of kernel methods. By means of a deep neural network, we learn a parametrized kernel…

Machine Learning · Computer Science 2020-12-14 Prudencio Tossou , Basile Dura , Francois Laviolette , Mario Marchand , Alexandre Lacoste

Attention mechanism has been extensively integrated within mainstream neural network architectures, such as Transformers and graph attention networks. Yet, its underlying working principles remain somewhat elusive. What is its essence? Are…

Machine Learning · Computer Science 2024-12-25 Tianyu Ruan , Shihua Zhang

In this paper we de ne conditional random elds in reproducing kernel Hilbert spaces and show connections to Gaussian Process classi cation. More speci cally, we prove decomposition results for undirected graphical models and we give…

Machine Learning · Computer Science 2012-07-19 Yasemin Altun , Alex Smola , Thomas Hofmann

In high-dimensional linear regression, the goal pursued here is to estimate an unknown regression function using linear combinations of a suitable set of covariates. One of the key assumptions for the success of any statistical procedure in…

Statistics Theory · Mathematics 2015-03-13 Philippe Rigollet , Alexandre Tsybakov

We develop a new framework for learning variational autoencoders and other deep generative models that balances generative and discriminative goals. Our framework optimizes model parameters to maximize a variational lower bound on the…

Machine Learning · Computer Science 2020-12-15 Gabriel Hope , Madina Abdrakhmanova , Xiaoyin Chen , Michael C. Hughes , Michael C. Hughes , Erik B. Sudderth