arXiv research

Transfer learning improves sentiment classification using XR framework.

We prove that the ends of a properly immersed simply or one connected minimal surface in H(2)xR contained in a slab of height less than πof H(2)xR, are multi-graphs. When such a surface is embedded then the ends are graphs. When embedded and simply connected, it is an entire graph.

XR improves search advertising relevance predictions.

XR-Transformer accelerates XMC by recursively fine-tuning on multi-resolution objectives.

We construct geometric barriers for minimal graphs in H^n xR. We prove the existence and uniqueness of a solution of the vertical minimal equation in the interior of a convex polyhedron in H^n extending continuously to the interior of each face, taking infinite boundary data on one face and zero boundary value data on …

Study on scattering geodesics on modular surface and their sojourn times.

Matrices satisfying the Restricted Isometry Property (RIP) play an important role in the areas of compressed sensing and statistical learning. RIP matrices with optimal parameters are mainly obtained via probabilistic arguments, as explicit constructions seem hard. It is therefore interesting to ask whether a fixed mat…

This paper investigates which smooth manifolds arise as quotients (orbit spaces) of flows of vector fields. Such quotient maps were already known to be surjective on fundamental groups, but this paper shows that every epimorphism of countably presented groups is induced by the quotient map of some flow, and that higher…

CascadeXML improves multi-resolution learning for XMC with transformer features.

While training a machine learning model using multiple workers, each of which collects data from their own data sources, it would be most useful when the data collected from different workers can be {\em unique} and {\em different}. Ironically, recent analysis of decentralized parallel stochastic gradient descent (D-PS…

Introduces AMLB, an open benchmark for AutoML frameworks.

EagerPy simplifies writing code for multiple deep learning frameworks.

OBSER framework infers sub-environments from objects, outperforming scene-based methods.

We propose a unified framework to speed up the existing stochastic matrix factorization (SMF) algorithms via variance reduction. Our framework is general and it subsumes several well-known SMF formulations in the literature. We perform a non-asymptotic convergence analysis of our framework and derive computational and …

A new forecasting framework uses suboptimal embeddings to improve multivariate time series prediction.

Extends DeTEcT framework for token economies with dynamic and probabilistic parameters.

New framework assesses and benchmarks ML methods for multivariate time series.

RYU framework constructs safe regions for optimization problems.

A modular framework for knowledge distillation simplifies experiments and reproducibility.

We give a combinatorial characterization of generic minimally rigid reflection frameworks. The main new idea is to study a pair of direction networks on the same graph such that one admits faithful realizations and the other has only collapsed realizations. In terms of infinitesimal rigidity, realizations of the former…

A new clustering framework using fixed points for data analysis.

The paper analyzes frameworks for integrating sustainability into investment decisions.

We explore a framework called boosted Markov networks to combine the learning capacity of boosting and the rich modeling semantics of Markov networks and applying the framework for video-based activity recognition. Importantly, we extend the framework to incorporate hidden variables. We show how the framework can be ap…

In this paper we introduce a flexible HJM-type framework that allows for consistent modelling of intraday, spot, futures, and option prices. This framework is based on stochastic processes with economic interpretations and consistent with the initial term structure given in the form of a price forward curve. Furthermor…

We present generalization bounds for the TS-MKL framework for two stage multiple kernel learning. We also present bounds for sparse kernel learning formulations within the TS-MKL framework.

PySAD offers a unified Python framework for efficient streaming anomaly detection.

TorchGAN simplifies GAN training and evaluation with a flexible framework.

DIVA clusters dynamic data without needing cluster count, outperforming baselines.

This paper introduces a new scalable multi-objective deep reinforcement learning (MODRL) framework based on deep Q-networks. We develop a high-performance MODRL framework that supports both single-policy and multi-policy strategies, as well as both linear and non-linear approaches to action selection. The experimental …

Unified framework for analyzing machine learning model attributions.

Unified framework for Bayesian online learning in changing conditions.

We present a probabilistic framework for nonlinearities, based on doubly truncated Gaussian distributions. By setting the truncation points appropriately, we are able to generate various types of nonlinearities within a unified framework, including sigmoid, tanh and ReLU, the most commonly used nonlinearities in neural…

ProbDR framework interprets DR algorithms as probabilistic inference.

The new framework for finance is proposed. This framework based on three known approaches in econophysics. Assumptions of the framework are the following: 1. For the majority of situations market follows non-arbitrage condition. 2. For the small number of situations market influenced by the actions of big firms. 3. If …

Framework solves bilevel optimization on manifolds.

We study the tracking problem, namely, estimating the hidden state of an object over time, from unreliable and noisy measurements. The standard framework for the tracking problem is the generative framework, which is the basis of solutions such as the Bayesian algorithm and its approximation, the particle filters. Howe…

The paper introduces a new framework for off-policy reinforcement learning.

We extend our generic rigidity theory for periodic frameworks in the plane to frameworks with a broader class of crystallographic symmetry. Along the way we introduce a new class of combinatorial matroids and associated linear representation results that may be interesting in their own right. The same techniques immedi…

A game-theoretic framework identifies influential hyperparameters for neural networks.

Graph-based methods provide a powerful tool set for many non-parametric frameworks in Machine Learning. In general, the memory and computational complexity of these methods is quadratic in the number of examples in the data which makes them quickly infeasible for moderate to large scale datasets. A significant effort t…

Proposes a new framework for discount models.

In real-world applications, not all instances in multi-view data are fully represented. To deal with incomplete data, Incomplete Multi-view Learning (IML) rises. In this paper, we propose the Joint Embedding Learning and Low-Rank Approximation (JELLA) framework for IML. The JELLA framework approximates the incomplete d…

This paper proposes a novel framework for fusing multi-temporal, multispectral satellite images and OpenStreetMap (OSM) data for the classification of local climate zones (LCZs). Feature stacking is the most commonly-used method of data fusion but does not consider the heterogeneity of multimodal optical images and OSM…

This study develops an online predictive optimization framework for dynamically operating a transit service in an area of crowd movements. The proposed framework integrates demand prediction and supply optimization to periodically redesign the service routes based on recently observed demand. To predict demand for the …

Unified statistical framework for LSTM model selection.

CFFL framework improves fairness in FL without sacrificing accuracy.

Chainer accelerates deep learning research with a flexible framework.

Proposes a Taylor framework to unify and analyze attribution methods.