English
Related papers

Related papers: On the Size and Width of the Decoder of a Boolean …

200 papers

Isolated training with Gaussian priors (TGP) of the component autoencoders of turbo-autoencoder architectures enables faster, more consistent training and better generalization to arbitrary decoding iterations than training based on deep…

Information Theory · Computer Science 2023-05-17 Jannis Clausius , Marvin Geiselhart , Stephan ten Brink

Graphs are ubiquitous data structures for representing interactions between entities. With an emphasis on the use of graphs to represent chemical molecules, we explore the task of learning to generate graphs that conform to a distribution…

Machine Learning · Computer Science 2019-03-08 Qi Liu , Miltiadis Allamanis , Marc Brockschmidt , Alexander L. Gaunt

The joint optimization of the reconstruction and classification error is a hard non convex problem, especially when a non linear mapping is utilized. In order to overcome this obstacle, a novel optimization strategy is proposed, in which a…

Machine Learning · Computer Science 2022-11-07 Ioannis A. Nellas , Sotiris K. Tasoulis , Vassilis P. Plagianakos , Spiros V. Georgakopoulos

Inspired by the success of deep learning techniques in the physical and chemical sciences, we apply a modification of an autoencoder type deep neural network to the task of dimension reduction of molecular dynamics data. We can show that…

Machine Learning · Statistics 2018-04-04 Christoph Wehmeyer , Frank Noé

Recently, Meta-Auto-Decoder (MAD) was proposed as a novel reduced order model (ROM) for solving parametric partial differential equations (PDEs), and the best possible performance of this method can be quantified by the decoder width. This…

Numerical Analysis · Mathematics 2023-06-27 Zhanhong Ye , Hongsheng Liu , Zidong Wang , Bin Dong

In this paper we give a compact presentation of the theory of abstract spaces for convolutional codes and convolutional encoders, and show a connection between them that seems to be missing in the literature. We use it for a short proof of…

Information Theory · Computer Science 2017-12-07 Štěpán Holub

Dense retrieval models have become a standard for state-of-the-art information retrieval. However, their high-dimensional, high-precision (float32) vector embeddings create significant storage and memory challenges for real-world…

Information Retrieval · Computer Science 2025-11-19 Satyanarayan Pati

The success of deep architectures is at least in part attributed to the layer-by-layer unsupervised pre-training that initializes the network. Various papers have reported extensive empirical analysis focusing on the design and…

Machine Learning · Computer Science 2015-02-13 Vamsi K Ithapu , Sathya Ravi , Vikas Singh

Imitation learning is an intuitive approach for teaching motion to robotic systems. Although previous studies have proposed various methods to model demonstrated movement primitives, one of the limitations of existing methods is that the…

Robotics · Computer Science 2020-09-24 Takayuki Osa , Shuhei Ikemoto

This paper proposes a bitwise over-parameterized neural network (ONN) decoder for polar-coded transmission and develops a tractable theoretical performance analysis framework. By modeling each synthesized message channel as an individual…

Signal Processing · Electrical Eng. & Systems 2026-05-01 Hongzhi Zhu , Wei Xu , Xiaohu You

Despite the recent developments that allowed neural networks to achieve impressive performance on a variety of applications, these models are intrinsically affected by the problem of overgeneralization, due to their partitioning of the full…

Artificial Intelligence · Computer Science 2020-02-11 Giacomo Spigler

Largest theoretical contribution to Neural Networks comes from VC Dimension which characterizes the sample complexity of classification model in a probabilistic view and are widely used to study the generalization error. So far in the…

Machine Learning · Computer Science 2024-09-05 Linu Pinto , Sasi Gopalan

Transformers have revolutionized the field of machine learning. In particular, they can be used to solve complex algorithmic problems, including graph-based tasks. In such algorithmic tasks a key question is what is the minimal size of a…

Machine Learning · Computer Science 2026-01-29 Gilad Yehudai , Clayton Sanford , Maya Bechler-Speicher , Orr Fischer , Ran Gilad-Bachrach , Amir Globerson

We present a simple neural rendering architecture that helps variational autoencoders (VAEs) learn disentangled representations. Instead of the deconvolutional network typically used in the decoder of VAEs, we tile (broadcast) the latent…

Machine Learning · Computer Science 2019-08-15 Nicholas Watters , Loic Matthey , Christopher P. Burgess , Alexander Lerchner

We formulate learning of a binary autoencoder as a biconvex optimization problem which learns from the pairwise correlations between encoded and decoded bits. Among all possible algorithms that use this information, ours finds the…

Machine Learning · Computer Science 2016-11-08 Akshay Balsubramani

Variational auto-encoders (VAEs) have proven to be a well suited tool for performing dimensionality reduction by extracting latent variables lying in a potentially much smaller dimensional space than the data. Their ability to capture…

Machine Learning · Statistics 2020-10-23 Clément Chadebec , Clément Mantoux , Stéphanie Allassonnière

Recently, the disentangled latent space of a variational autoencoder (VAE) has been used to reason about multi-label out-of-distribution (OOD) test samples that are derived from different distributions than training samples. Disentangled…

Machine Learning · Computer Science 2025-12-12 Zahra Rahiminasab , Michael Yuhas , Arvind Easwaran

Aligned latent spaces, where meaningful semantic shifts in the input space correspond to a translation in the embedding space, play an important role in the success of downstream tasks such as unsupervised clustering and data imputation. In…

Machine Learning · Computer Science 2021-06-30 Saachi Jain , Adityanarayanan Radhakrishnan , Caroline Uhler

We develop a method for training neural networks on Boolean data in which the values at all nodes are strictly $\pm 1$, and the resulting models are typically equivalent to networks whose nonzero weights are also $\pm 1$. The method…

Machine Learning · Computer Science 2026-02-20 Veit Elser , Manish Krishan Lal

We explore the expressive power of Transformers by establishing precise approximation error upper and lower bounds for H\"{o}lder class. Specifically, a new approximation upper bound is derived for the standard Transformer architecture…

Machine Learning · Computer Science 2026-05-11 Xin He , Yuling Jiao , Xiliang Lu , Jerry Zhijian Yang
‹ Prev 1 4 5 6 7 8 10 Next ›