Enhances fault tolerance of neural networks for security-critical applications.
problem Fault tolerance of neural networks is biased and can lead to severe consequences in security-critical scenarios.
method Proposes a revised implementation that significantly enhances the fault tolerance property of neural networks with detailed mathematical analysis.
result Significantly increased fault tolerance of neural networks for security-critical applications.
Paper proposes EMO-based AE generation for black-box settings.
problem Designing robust adversarial examples for black-box models.
method Evolutionary Multi-objective Optimization (EMO) for generating various types of adversarial examples.
result EMO-based method generates AEs that are robust and applicable to high-resolution images.
AES scheme improves Bermudan and American option pricing for Heston models.
problem Pricing Bermudan and American options under Heston models efficiently.
method AES scheme using non-central chi-square distribution for variance process.
result AES achieves higher accuracy and computational efficiency for Bermudan options.
Fisher auto-encoders use Fisher divergence for more robust generative modeling.
problem Model uncertainty in generative models.
method Minimizing Fisher divergence between true and modeled joint distributions.
result Fisher auto-encoders can more accurately quantify model uncertainty.
Deep neural networks (DNNs) have shown huge superiority over humans in image recognition, speech processing, autonomous vehicles and medical diagnosis. However, recent studies indicate that DNNs are vulnerable to adversarial examples (AEs), which are designed by attackers to fool deep learning models. Different from re…
Proposes flexible auto-encoders for varying data dimensions.
problem Fixed latent dimensions limit data flexibility.
method Stochastic bottleneck with weighted dropouts.
result Seamless variable dimensionality reduction with high performance.
FastGAE scales graph AE and VAE to large graphs with millions of nodes.
problem Scalability issues in graph AE and VAE.
method Stochastic subgraph decoding scheme to speed up training.
result Outperforms existing approaches on various real-world graphs.
New bounds on AE success probability in GP models.
problem Limiting the success of adversarial examples in probabilistic models.
method Investigated upper bounds on AE success probability using Gaussian Processes.
result Proved a new upper bound of AE success probability dependent on perturbation norm, kernel function, and training dataset distance.
In this paper, we suggest a framework to make use of mutual information as a regularization criterion to train Auto-Encoders (AEs). In the proposed framework, AEs are regularized by minimization of the mutual information between input and encoding variables of AEs during the training phase. In order to estimate the ent…
New research shows non-bottlenecked autoencoders can outperform bottlenecked ones for anomaly detection.
problem The necessity of a bottleneck in autoencoders for anomaly detection.
method Investigated two ways to remove bottlenecks: overparameterising the latent layer and introducing skip connections. Carried out extensive experiments on various AE types and datasets.
result Non-bottlenecked autoencoders can outperform bottlenecked ones, improving anomaly detection performance.
Improves unsupervised feature learning with an exclusivity concept.
problem Overfitting in AE-based unsupervised feature learning.
method Integrates exclusivity concept to enhance AE's latent feature representation.
result Significant improvement in performance compared to other methods.
This paper proposes BAT to balance accuracy and robustness in adversarial training.
problem Balancing accuracy and robustness in adversarial training models.
method Blind adversarial training (BAT) uses a cutoff-scale strategy to adaptively estimate a nonuniform budget for AEs.
result BAT improves the overall robustness of adversarial training models.
VCAE uses vine copulas to improve AE generative models for high-dimensional data.
problem Creating flexible generative models for high-dimensional data.
method Three-step procedure: autoencoder compression, vine copula estimation, and generative model combination.
result VCAEs achieve competitive results compared to standard baselines.
New graph AE and VAE model predicts directed links better than existing methods.
problem Link prediction in directed graphs, especially for unobserved edges.
method Gravity-inspired decoder scheme for directed graphs.
result Outperforms standard graph AE and VAE on three real-world directed link prediction tasks.
New insights into Deep Autoencoders for better data approximation and generalization.
problem Understanding and improving generalization of deep learning models with more parameters than data.
method Interpreting Deep Autoencoders' structure and using Lie group theory for regularization.
result Regularizations enable Deep Autoencoders to better approximate data manifolds and generalize.
AES improves policy gradient performance by adaptively selecting experience.
problem High variance in gradient estimators from past trajectories.
method AES learns an adaptive sampling distribution to minimise gradient variance.
result AES leads to significantly improved performance in continuous control tasks.
Simple linear model outperforms GCN in graph AE tasks.
problem Challenging tasks like link prediction and node clustering.
method Replaced GCN with a simple linear model on adjacency matrix.
result Simple model consistently reaches competitive performances.
AE-LSVI identifies near-optimal policies in complex systems with minimal data.
problem Identifying near-optimal policies in complex, costly data acquisition systems.
method Combines optimism and pessimism for active exploration in a generative model setting.
result Proves near-optimal policy identification over entire state spaces with polynomial sample complexity.
Double autoencoder Ae2I improves missing value imputation in recommender systems.
problem Imputing missing values in tables using row-row and column-column relationships.
method Simultaneously uses row-row and column-column relationships through a double autoencoder.
result Ae2I outperforms state-of-the-art models in recommender systems. Simpler linear models outperform complex GCN encoders for graph tasks.
problem Complex graph autoencoders and variational autoencoders.
method Replacing GCN encoders with one-hop linear models.
result Simpler linear models achieve competitive performance with fewer operations and parameters.
New framework scales graph AE and VAE by training on a subset of nodes.
problem Training scalability and speed issues in graph AE and VAE models.
method Utilizes graph degeneracy to train on a dense subset of nodes, with a propagation mechanism.
result Empirically competitive results on large graphs (millions of nodes and edges).
Many engineering problems require identifying feasible domains under implicit constraints. One example is finding acceptable car body styling designs based on constraints like aesthetics and functionality. Current active-learning based methods learn feasible domains for bounded input spaces. However, we usually lack pr…
Proposes MC-AE for better unsupervised clustering of unlabeled data.
problem Lack of consideration for multi-local collaborative relationships in autoencoders.
method Integrates LSH for multi-local cross blocks, mcrRBM and mcrGRBM models.
result MC-AE improves unsupervised clustering performance.
AES uses α-divergence to select informative points for BO, improving optimization performance.
problem Optimizing complex functions with limited evaluations.
method AES uses α-divergence to select points based on dependency with global maximum.
result AES outperforms other information-based acquisition functions in various experiments.
Proposes AE for robust PCA, improving robustness to outliers.
problem PCA's sensitivity to outliers.
method Angular Embedding (AE) and Truncated Angular Embedding (TAE).
result AE/TAE outperforms state-of-the-art RPCA methods.
Enhances financial data signal-to-noise ratio using auto-encoders and mutual regularization.
problem Improving signal-to-noise ratio in financial data.
method Combining target and context variables, using auto-encoders with mutual regularization to learn common ground.
result Discover new regularities in financial time-series data.
We present a neural network architecture based upon the Autoencoder (AE) and Generative Adversarial Network (GAN) that promotes a convex latent distribution by training adversarially on latent space interpolations. By using an AE as both the generator and discriminator of a GAN, we pass a pixel-wise error function acro…
A new framework converts EEG signals between subjects and tasks.
problem Noise and variability in EEG data hinder generalizable signal extraction.
method Contrastive Split-Latent Permutation Autoencoder (CSLP-AE) framework.
result The CSLP-AE framework enables zero-shot conversion between unseen subjects.
Generative Adversarial Networks (GANs) have been used in many different applications to generate realistic synthetic data. We introduce a novel GAN with Autoencoder (GAN-AE) architecture to generate synthetic samples for variable length, multi-feature sequence datasets. In this model, we develop a GAN architecture with…
Common Representation Learning (CRL), wherein different descriptions (or views) of the data are embedded in a common subspace, is receiving a lot of attention recently. Two popular paradigms here are Canonical Correlation Analysis (CCA) based approaches and Autoencoder (AE) based approaches. CCA based approaches learn …
Automated anomaly detection is essential for managing information and communications technology (ICT) systems to maintain reliable services with minimum burden on operators. For detecting varying and continually emerging anomalies as differences from normal states, learning normal relationships inherent among cross-dom…
Cencelj and Dranishnikov showed that for certain nilpotent groups G, K(Gab,1)∈AE(X) is equivalent to K(G,1)∈AE(X) for any compacta X (here Gab is the abelianization of G). We examine the same problem for solvable groups. We also give an elementary proof of this fact for any nilpo…
In this paper we study properties of the area evolute (AE) and the center symmetry set (CSS) of a convex planar curve γ. The main tool is to define a Minkowski plane where γ becomes a constant width curve. In this Minkowski plane, the CSS is the evolute of γ and the AE is an involute of the CSS. We prove that the…
We prove that for a compact subgroup H of an almost connected locally compact Hausdorff group G, the following properties are mutually equivalent: (1) H is a maximal compact subgroup of G, (2) G/H is contractible, (3) G/H is homeomorphic to a Euclidean space, (4) G/H is an AE for paracompact spaces, (5) $…
The main point of this paper is to prove the following useful result: If the almost everywhere 2-jet of a locally quasi-convex function u satisfies a degenerate elliptic constraint F, then u is F-subharmonic, i.e., u is a viscosity F-subsolution. This AE Theorem makes otherwise difficult results transparent. Some insta…
Improves stability in hyperbolic neural networks for complex data generation.
problem Numerical instability in hyperbolic neural networks hinders complex architecture development.
method Proposes a novel hyperbolic AE-GAN architecture with stable layers.
result Demonstrates state-of-the-art performance in generating complex data.
The paper proves existence of solutions for Einstein-type elliptic systems on AE manifolds.
problem Analyzing semi-linear systems of partial differential equations motivated by the conformal formulation of Einstein constraint equations.
method Proving existence theorems under suitable conditions, including smallness assumptions on free parameters.
result Existence of far from CMC (near CMC) Yamabe positive (Yamabe non-positive) solutions for charged dust coupled to the Einstein equations.
Recently, deep learning becomes the main focus of machine learning research and has greatly impacted many important fields. However, deep learning is criticized for lack of interpretability. As a successful unsupervised model in deep learning, the autoencoder embraces a wide spectrum of applications, yet it suffers fro…
FlexAE addresses bias-variance trade-off in RAEs by learning latent priors.
problem Improving generation quality of deterministic AE models.
method Introducing flexibly learnable latent priors in WAEs to optimize the latent distribution.
result FlexAE achieves state-of-the-art performance in AE-based generative models.
This paper proposes a novel optimization principle and its implementation for unsupervised anomaly detection in sound (ADS) using an autoencoder (AE). The goal of unsupervised-ADS is to detect unknown anomalous sound without training data of anomalous sound. Use of an AE as a normal model is a state-of-the-art techniqu…
Paper proves rigidity theorems for AE Q-singular spaces.
problem Analyzing Q-curvature on AE manifolds. method Introducing a fourth order energy and rewriting it in terms of a fourth order Ricci-like tensor.
result Yamabe positive J-flat AE manifolds are isometric to Euclidean space. Paper improves channel charting using autoencoders with spatial constraints.
problem Improving logical positioning of UEs using channel-state information.
method Representation-constrained autoencoders to enhance channel charts.
result Improved quality of learned channel charts for UE positioning.
GMMSEQ clusters AE data streams, identifying cluster onsets and growth.
problem Clustering unlabeled AE data with onsets and growth information.
method Modified Gaussian Mixture Models (GMM) with an objective function for AE timestamps.
result GMMSEQ provides better cluster characterization than standard methods.
Two methods estimate effect size for online experiments, improving accuracy and efficiency.
problem Determining the correct effect size for online experiment duration.
method Two approaches: hierarchical models and utility theory.
result Proposed methods outperform baseline approaches in accuracy and efficiency.
AE-DDPG improves DDPG for continuous control in complex environments with less data and time.
problem Data insufficiency and training inefficiency in DDPG for complex environments.
method Asynchronous episodic data collection, modified experience replay, and new action noise.
result AE-DDPG achieves higher rewards and less training time in complex environments.
SentenceMIM learns rich latent representations for variable-length language data.
problem Challenges in learning VAEs for variable-length language data, especially posterior collapse.
method Probabilistic auto-encoder trained with Mutual Information Machine (MIM) learning.
result SentenceMIM learns informative latent representations with high mutual information.
We propose a K-sparse exhaustive search (ES-K) method and a K-sparse approximate exhaustive search method (AES-K) for selecting variables in linear regression. With these methods, K-sparse combinations of variables are tested exhaustively assuming that the optimal combination of explanatory variables is K-sparse. By co…
New distances for comparing heterogeneous probability measures efficiently.
problem Comparing probability measures across different spaces.
method Introducing Anchor Energy (AE) and Anchor Wasserstein (AW) distances, and a sweep line algorithm for exact computation.
result Exact computation of AE and AW distances in log-quadratic time, significantly faster than GW.