A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
This paper improves STL inference reliability under covariate shift.
We develop a scale-invariant truncated Lévy (STL) process to describe physical systems characterized by correlated stochastic variables. The STL process exhibits Lévy stability for the probability density, and hence shows scaling properties (as observed in empirical data); it has the advantage that all moments are fini…
Kernel for STL formulae enables machine learning in temporal logic.
New technique learns STL formulas for classifying time-series data.
STL-SGD accelerates Local SGD by gradually increasing communication periods.
Combines neural networks and STL for multi-class time-series classification.
BBVI with STL converges geometrically under perfect specification, with quadratic variance bound.
Paper tackles reinforcement learning for STL specifications with state history.
Study uses DRL with Lagrangian relaxation to solve temporal control tasks with STL constraints.
Proposes combining SARIMA and STL for real-time anomaly detection.
Visual reranking is effective to improve the performance of the text-based video search. However, existing reranking algorithms can only achieve limited improvement because of the well-known semantic gap between low level visual features and high level semantic concepts. In this paper, we adopt interactive video search…
Algorithm mines environment assumptions for cyber-physical systems.
We study the total least squares (TLS) problem that generalizes least squares regression by allowing measurement errors in both dependent and independent variables. TLS is widely used in applied fields including computer vision, system identification and econometrics. The special case when all dependent and independent…
This work improves SINDy-type algorithms for system identification using score-guided dictionary selection.
End-to-end analysis of SGD for STL with adaptive sub-sampling.
Paper proposes a new method to protect model information in multi-task learning.
In this paper, we introduce a new model for leveraging unlabeled data to improve generalization performances of image classifiers: a two-branch encoder-decoder architecture called HybridNet. The first branch receives supervision signal and is dedicated to the extraction of invariant class-related representations. The s…
Heat demand prediction is a prominent research topic in the area of intelligent energy networks. It has been well recognized that periodicity is one of the important characteristics of heat demand. Seasonal-trend decomposition based on LOESS (STL) algorithm can analyze the periodicity of a heat demand series, and decom…
Scale-equivariant CNNs handle scale changes for improved performance.
AGAN automates GAN design, outperforming human-designed models.
Soft Truncation improves diffusion model performance by balancing loss scales across diffusion times.
BetaDataWeighter learns weights for unlabelled data to improve self-supervised learning accuracy.
Certified guidance ensures generative models always meet planning objectives.
Meta-Semi learns to optimize SSL with minimal hyper-parameter tuning.
This paper describes a new method for low rank kernel approximation called IKA. The main advantage of IKA is that it produces a function defined as a linear combination of arbitrarily chosen functions. In contrast the approximation produced by Nyström method is a linear combination of kernel evaluations. The pro…
AISLE framework improves on IWAE by directly optimising proposal distribution.
One of the challenges in the study of generative adversarial networks is the instability of its training. In this paper, we propose a novel weight normalization technique called spectral normalization to stabilize the training of the discriminator. Our new normalization technique is computationally light and easy to in…
A new mutual information optimization method using self-supervised binary contrastive learning.
Deep neural networks are a powerful tool for feature learning and extraction given their ability to model high-level abstractions in highly complex data. One area worth exploring in feature learning and extraction using deep neural networks is efficient neural connectivity formation for faster feature learning and extr…
Generative Adversarial Networks (GANs) produce systematically better quality samples when class label information is provided., i.e. in the conditional GAN setup. This is still observed for the recently proposed Wasserstein GAN formulation which stabilized adversarial training and allows considering high capacity netwo…
Discriminator optimizes to approximate optimal transport for better image generation.
Most existing GANs architectures that generate images use transposed convolution or resize-convolution as their upsampling algorithm from lower to higher resolution feature maps in the generator. We argue that this kind of fixed operation is problematic for GANs to model objects that have very different visual appearan…
This study compares mtl architectures for renewable power generation forecasting.
FedMCC learns from distributed data to cluster and extract features.
DIVE learns video representations even with missing data.
Learning invariant representations is an important problem in machine learning and pattern recognition. In this paper, we present a novel framework of transformation-invariant feature learning by incorporating linear transformations into the feature learning algorithms. For example, we present the transformation-invari…
In many problems of supervised tensor learning (STL), real world data such as face images or MRI scans are naturally represented as matrices, which are also called as second order tensors. Most existing classifiers based on tensor representation, such as support tensor machine (STM) need to solve iteratively which occu…
Motivated by an important insight from neural science, we propose a new framework for understanding the success of the recently proposed "maxout" networks. The framework is based on encoding information on sparse pathways and recognizing the correct pathway at inference time. Elaborating further on this insight, we pro…
An important goal in visual recognition is to devise image representations that are invariant to particular transformations. In this paper, we address this goal with a new type of convolutional neural network (CNN) whose invariance is encoded by a reproducing kernel. Unlike traditional approaches where neural networks …
New method reduces version space for CNNs, improving active learning performance.
We examine two different techniques for parameter averaging in GAN training. Moving Average (MA) computes the time-average of parameters, whereas Exponential Moving Average (EMA) computes an exponentially discounted sum. Whilst MA is known to lead to convergence in bilinear settings, we provide the -- to our knowledge …
Improved deep dynamics models with symmetries for better accuracy and generalization.
MixMatch combines unlabeled data with labeled data to improve semi-supervised learning.
New framework improves GAN training by controlling weight spectra.
Recently, deep residual networks have been successfully applied in many computer vision and natural language processing tasks, pushing the state-of-the-art performance with deeper and wider architectures. In this work, we interpret deep residual networks as ordinary differential equations (ODEs), which have long been s…
We consider the problem of using a factor model we call {\em spike-and-slab sparse coding} (S3C) to learn features for a classification task. The S3C model resembles both the spike-and-slab RBM and sparse coding. Since exact inference in this model is intractable, we derive a structured variational inference procedure …
GraN-GAN normalizes gradients for better GAN performance.
Multipath is among the major sources of errors in precise positioning using GPS and continues to be extensively studied. Two Fast Fourier Transform (FFT)-based detectors are presented in this paper as GPS multipath detection techniques. The detectors are formulated as binary hypothesis tests under the assumption that t…