English
Related papers

Related papers: Set Cross Entropy: Likelihood-based Permutation In…

200 papers

Permutation invariant neural networks are a promising tool for making predictions from sets. However, we show that existing permutation invariant architectures, Deep Sets and Set Transformer, can suffer from vanishing or exploding gradients…

Machine Learning · Computer Science 2022-07-15 Lily H. Zhang , Veronica Tozzo , John M. Higgins , Rajesh Ranganath

Quantifying the complexity of large graphs requires measures that extend beyond predefined structural features and scale efficiently with graph size. This work adopts a generative perspective, modeling large networks as exchangeable graphs…

Information Theory · Computer Science 2025-03-14 Anda Skeja , Sofia C. Olhede

Gathering the most information by picking the least amount of data is a common task in experimental design or when exploring an unknown environment in reinforcement learning and robotics. A widely used measure for quantifying the…

Machine Learning · Statistics 2015-09-17 Johannes Kulick , Robert Lieck , Marc Toussaint

Improving the classification of multi-class imbalanced data is more difficult than its two-class counterpart. In this paper, we use deep neural networks to train new representations of tabular multi-class data. Unlike the typically…

Machine Learning · Computer Science 2023-12-19 Damian Horna , Lango Mateusz , Jerzy Stefanowski

Supervised image segmentation assigns image voxels to a set of labels, as defined by a specific labeling protocol. In this paper, we decompose segmentation into two steps. The first step is what we call "primitive segmentation", where…

Image and Video Processing · Electrical Eng. & Systems 2018-09-07 Sundaresh Ram , Mert R. Sabuncu

We present a new paradigm for speeding up randomized computations of several frequently used functions in machine learning. In particular, our paradigm can be applied for improving computations of kernels based on random embeddings. Above…

Machine Learning · Statistics 2016-04-26 Krzysztof Choromanski , Francois Fagan

Recovering the digital input of a time-discrete linear system from its (noisy) output is a significant challenge in the fields of data transmission, deconvolution, channel equalization, and inverse modeling. A variety of algorithms have…

Optimization and Control · Mathematics 2020-12-03 Sophie M. Fosson

Maximum entropy principle (MEP) offers an effective and unbiased approach to inferring unknown probability distributions when faced with incomplete information, while neural networks provide the flexibility to learn complex distributions…

Machine Learning · Statistics 2024-12-04 Wuyue Yang , Liangrong Peng , Guojie Li , Liu Hong

In the past few years, triplet loss-based metric embeddings have become a de-facto standard for several important computer vision problems, most no-tably, person reidentification. On the other hand, in the area of speech recognition the…

Audio and Speech Processing · Electrical Eng. & Systems 2022-02-08 Roman Vygon , Nikolay Mikhaylovskiy

In this work, we present a distributed framework based on the graph algorithm for computing control invariant set for nonlinear cascade systems. The proposed algorithm exploits the structure of the interconnections within a process network.…

Systems and Control · Electrical Eng. & Systems 2022-05-12 Benjamin Decardi-Nelson , Jinfeng Liu

We study the problem of designing models for machine learning tasks defined on \emph{sets}. In contrast to traditional approach of operating on fixed dimensional vectors, we consider objective functions defined on sets that are invariant to…

Machine Learning · Computer Science 2018-04-17 Manzil Zaheer , Satwik Kottur , Siamak Ravanbakhsh , Barnabas Poczos , Ruslan Salakhutdinov , Alexander Smola

This paper proposes a method to construct pretext tasks for self-supervised learning on group equivariant neural networks. Group equivariant neural networks are the models whose structure is restricted to commute with the transformations on…

Computer Vision and Pattern Recognition · Computer Science 2023-03-09 Yusuke Mukuta , Tatsuya Harada

In the classical source coding problem, the compressed source is reconstructed at the decoder with respect to some distortion metric. Motivated by settings in which we are interested in more than simply reconstructing the compressed source,…

Information Theory · Computer Science 2023-10-03 Oğuzhan Kubilay Ülger , Elza Erkip

In numerous practical applications, especially in medical image reconstruction, it is often infeasible to obtain a large ensemble of ground-truth/measurement pairs for supervised learning. Therefore, it is imperative to develop unsupervised…

Image and Video Processing · Electrical Eng. & Systems 2021-03-31 Subhadip Mukherjee , Ozan Öktem , Carola-Bibiane Schönlieb

We combine concept-based neural networks with generative, flow-based classifiers into a novel, intrinsically explainable, exactly invertible approach to supervised learning. Prototypical neural networks, a type of concept-based neural…

Machine Learning · Computer Science 2024-07-18 Zachariah Carmichael , Timothy Redgrave , Daniel Gonzalez Cedre , Walter J. Scheirer

We propose a simple discrete time semi-supervised graph embedding approach to link prediction in dynamic networks. The learned embedding reflects information from both the temporal and cross-sectional network structures, which is performed…

Machine Learning · Statistics 2016-10-17 Ryohei Hisano

Network representation learning has exploded recently. However, existing studies usually reconstruct networks as sequences or matrices, which may cause information bias or sparsity problem during model training. Inspired by a cognitive…

Machine Learning · Computer Science 2019-10-01 Jie Bai , Linjing Li , Daniel Zeng

This letter introduces an abstract learning problem called the "set embedding": The objective is to map sets into probability distributions so as to lose less information. We relate set union and intersection operations with corresponding…

Machine Learning · Computer Science 2019-12-13 Ke Sun , Frank Nielsen

The R\'{e}nyi cross-entropy measure between two distributions, a generalization of the Shannon cross-entropy, was recently used as a loss function for the improved design of deep learning generative adversarial networks. In this work, we…

Information Theory · Computer Science 2022-08-09 Ferenc Cole Thierrin , Fady Alajaji , Tamás Linder

The objective of drug discovery is to identify chemical compounds that possess specific pharmaceutical properties toward a binding target. Existing large language models (LLMS) can achieve high token matching scores in terms of likelihood…

Machine Learning · Computer Science 2025-04-01 Xuefeng Liu , Chih-chan Tien , Peng Ding , Songhao Jiang , Rick L. Stevens
‹ Prev 1 8 9 10 Next ›