English
Related papers

Related papers: Sparse and Continuous Attention Mechanisms

200 papers

We propose sparsemax, a new activation function similar to the traditional softmax, but able to output sparse probabilities. After deriving its properties, we show how its Jacobian can be efficiently computed, enabling its use in a network…

Computation and Language · Computer Science 2016-02-09 André F. T. Martins , Ramón Fernandez Astudillo

The softmax function is widely used in artificial neural networks for the multiclass classification problems, where the softmax transformation enforces the output to be positive and sum to one, and the corresponding loss function allows to…

Machine Learning · Computer Science 2021-12-24 Shaoshi Sun , Zhenyuan Zhang , BoCheng Huang , Pengbin Lei , Jianlin Su , Shengfeng Pan , Jiarun Cao

Derivatives, as a critical class of financial instruments, isolate and trade the price attributes of risk assets such as stocks, commodities, and indices, aiding risk management and enhancing market efficiency. However, traditional hedging…

Computational Finance · Quantitative Finance 2025-03-07 Yiheng Ding , Gangnan Yuan , Dewei Zuo , Ting Gao

While CNNs naturally lend themselves to densely sampled data, and sophisticated implementations are available, they lack the ability to efficiently process sparse data. In this work we introduce a suite of tools that exploit sparsity in…

Computer Vision and Pattern Recognition · Computer Science 2020-03-13 Timo Hackel , Mikhail Usvyatsov , Silvano Galliani , Jan D. Wegner , Konrad Schindler

Transformer architectures, and their attention mechanisms in particular, form the foundation of modern large language models. While transformer models are widely believed to operate in high-dimensional hidden spaces, we show that attention…

Machine Learning · Computer Science 2026-02-12 Junxuan Wang , Xuyang Ge , Wentao Shu , Zhengfu He , Xipeng Qiu

In this paper, we focus on statistical region-based active contour models where image features (e.g. intensity) are random variables whose distribution belongs to some parametric family (e.g. exponential) rather than confining ourselves to…

Computer Vision and Pattern Recognition · Computer Science 2008-05-22 François Lecellier , Stéphanie Jehan-Besson , Jalal Fadili , Gilles Aubert , Marinette Revenu

In classification tasks, softmax functions are ubiquitously used as output activations to produce predictive probabilities. Such outputs only capture aleatoric uncertainty. To capture epistemic uncertainty, approximate Gaussian inference…

Machine Learning · Computer Science 2026-02-12 Bálint Mucsányi , Nathaël Da Costa , Philipp Hennig

Sparse deep learning has become a popular technique for improving the performance of deep neural networks in areas such as uncertainty quantification, variable selection, and large-scale network compression. However, most existing research…

Machine Learning · Statistics 2023-10-06 Mingxuan Zhang , Yan Sun , Faming Liang

In the context of adaptive Monte Carlo algorithms, we cannot directly generate independent samples from the distribution of interest but use a proxy which we need to be close to the target. Generally, such a proxy distribution is a…

Statistics Theory · Mathematics 2011-11-15 Christian Schäfer

The diffusion strategy for distributed learning from streaming data employs local stochastic gradient updates along with exchange of iterates over neighborhoods. In Part I [2] of this work we established that agents cluster around a network…

Multiagent Systems · Computer Science 2019-07-04 Stefan Vlaski , Ali H. Sayed

Categorical distributions are ubiquitous in machine learning, e.g., in classification, language models, and recommendation systems. However, when the number of possible outcomes is very large, using categorical distributions becomes…

Machine Learning · Statistics 2018-06-08 Francisco J. R. Ruiz , Michalis K. Titsias , Adji B. Dieng , David M. Blei

Flexible models for probability distributions are an essential ingredient in many machine learning tasks. We develop and investigate a new class of probability distributions, which we call a Squared Neural Family (SNEFY), formed by squaring…

Machine Learning · Computer Science 2023-10-27 Russell Tsuchida , Cheng Soon Ong , Dino Sejdinovic

Driven by the need to solve increasingly complex optimization problems in signal processing and machine learning, there has been increasing interest in understanding the behavior of gradient-descent algorithms in non-convex environments.…

Optimization and Control · Mathematics 2019-07-04 Stefan Vlaski , Ali H. Sayed

We are concerned with learning models that generalize well to different \emph{unseen} domains. We consider a worst-case formulation over data distributions that are near the source domain in the feature space. Only using training data from…

Computer Vision and Pattern Recognition · Computer Science 2018-11-07 Riccardo Volpi , Hongseok Namkoong , Ozan Sener , John Duchi , Vittorio Murino , Silvio Savarese

Sparse attention offers a promising strategy to extend long-context capabilities in Transformer LLMs, yet its efficiency-accuracy trade-offs remain unclear due to the lack of comprehensive evaluation. We address this gap with the…

Computation and Language · Computer Science 2026-01-28 Piotr Nawrot , Robert Li , Renjie Huang , Sebastian Ruder , Kelly Marchisio , Edoardo M. Ponti

Softmax attention maps every query--key interaction into a probability distribution, but the underlying structure remains largely unexplored. We define the \emph{energy field}, the row-centered attention logit, and show that it exhibits…

Machine Learning · Computer Science 2026-05-06 Wonsuk Lee

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

In NMT, words are sometimes dropped from the source or generated repeatedly in the translation. We explore novel strategies to address the coverage problem that change only the attention transformation. Our approach allocates fertilities to…

Computation and Language · Computer Science 2018-05-23 Chaitanya Malaviya , Pedro Ferreira , André F. T. Martins

Decomposing model activations into interpretable components is a key open problem in mechanistic interpretability. Sparse autoencoders (SAEs) are a popular method for decomposing the internal activations of trained transformers into sparse,…

Machine Learning · Computer Science 2024-06-26 Connor Kissane , Robert Krzyzanowski , Joseph Isaac Bloom , Arthur Conmy , Neel Nanda

We propose a novel framework, Continuous_Time Attention, which infuses partial differential equations (PDEs) into the Transformer's attention mechanism to address the challenges of extremely long input sequences. Instead of relying solely…

Machine Learning · Computer Science 2025-12-30 Yukun Zhang , Xueqing Zhou
‹ Prev 1 3 4 5 6 7 10 Next ›