arXiv research

GAICF proposes a framework for governing generative AI in banking.

GAICF proposes a framework for managing generative AI risks in banking.

Let $(M,g)$ be a closed, oriented, Riemannian manifold of dimension $m$. We call a systole a shortest non-contractible loop in $(M,g)$ and denote by $sys(M,g)$ its length. Let $SR(M,g)=\frac{{sys(M,g)}^m}{vol(M,g)}$ be the systolic ratio of $(M,g)$. Denote by $SR(k)$ the supremum of $SR(S,g)$ among the surfaces of fixe…

PAN+SR tackles scalable symbolic regression for large $p$ datasets.

Financial markets are exposed to systemic risk (SR), the risk that a major fraction of the system ceases to function, and collapses. It has recently become possible to quantify SR in terms of underlying financial networks where nodes represent financial institutions, and links capture the size and maturity of assets (l…

The paper discovers and evaluates support and resistance levels in financial time series.

GFN-SR uses deep learning to generate diverse mathematical expressions.

Active learning improves SR by proposing experiments in data-limited settings.

Complete integrability proved for SR geodesic flow on S^7.

In this paper, we give a complete description of all translation hypersurfaces with constant r-curvature Sr, in the Euclidean space.

While Convolutional Neural Networks (CNNs) trained for image and video super-resolution (SR) regularly achieve new state-of-the-art performance, they also suffer from significant drawbacks. One of their limitations is their lack of robustness to unseen image formation models during training. Other limitations include t…

A new model learns preferences incrementally without personal data.

Probabilistic SR method speeds up high-fidelity simulations with reliable uncertainty estimates.

Improved algorithm for clustered Federated Learning reduces initialization and hyperparameter requirements.

Large companies need to monitor various metrics (for example, Page Views and Revenue) of their applications and services in real time. At Microsoft, we develop a time-series anomaly detection service which helps customers to monitor the time-series continuously and alert for potential incidents on time. In this paper, …

For an oriented link diagram D, the warping degree d(D) is the smallest number of crossing changes which are needed to obtain a monotone diagram from D. We show that d(D)+d(-D)+sr(D) is less than or equal to the crossing number of D, where -D denotes the inverse of D and sr(D) denotes the number of components which hav…

The paper describes superconformal structures on super Riemann surfaces using fatgraphs.

The dictionary-aided sparse regression (SR) approach has recently emerged as a promising alternative to hyperspectral unmixing (HU) in remote sensing. By using an available spectral library as a dictionary, the SR approach identifies the underlying materials in a given hyperspectral image by selecting a small subset of…

We present a detailed study of the performance of a trading rule that uses moving average of past returns to predict future returns on stock indexes. Our main goal is to link performance and the stochastic process of the traded asset. Our study reports short, medium and long term effects by looking at the Sharpe ratio …

The paper examines how ESG constraints affect portfolio optimization in large datasets.

Strongly log-concave (SLC) distributions are a rich class of discrete probability distributions over subsets of some ground set. They are strictly more general than strongly Rayleigh (SR) distributions such as the well-known determinantal point process. While SR distributions offer elegant models of diversity, they lac…

Enhances traditional MV model for socially responsible investors.

This paper motivates and develops source traces for temporal difference (TD) learning in the tabular setting. Source traces are like eligibility traces, but model potential histories rather than immediate ones. This allows TD errors to be propagated to potential causal states and leads to faster generalization. Source …

Image super-resolution (SR) is an underdetermined inverse problem, where a large number of plausible high-resolution images can explain the same downsampled image. Most current single image SR methods use empirical risk minimisation, often with a pixel-wise mean squared error (MSE) loss. However, the outputs from such …

Active-set algorithm improves Cox regression for shape-restricted covariates.

We propose sequenced-replacement sampling (SRS) for training deep neural networks. The basic idea is to assign a fixed sequence index to each sample in the dataset. Once a mini-batch is randomly drawn in each training iteration, we refill the original dataset by successively adding samples according to their sequence i…

Matching Pursuit LASSIn Part I \cite{TanPMLPart1}, a Matching Pursuit LASSO ({MPL}) algorithm has been presented for solving large-scale sparse recovery (SR) problems. In this paper, we present a subspace search to further improve the performance of MPL, and then continue to address another major challenge of SR -- bat…

Optimized Sharpe Ratio for better risk-adjusted decision-making in multi-armed bandits.

Recently, several models based on deep neural networks have achieved great success in terms of both reconstruction accuracy and computational performance for single image super-resolution. In these methods, the low resolution (LR) input image is upscaled to the high resolution (HR) space using a single filter, commonly…

As Super-Resolution (SR) has matured as a research topic, it has been applied to additional topics beyond image reconstruction. In particular, combining classification or object detection tasks with a super-resolution preprocessing stage has yielded improvements in accuracy especially with objects that are small relati…

We give a new proof of the existence (\cite{HM}, \cite{Ren}) of a Jenkins-Strebel differential $Φ$ on a Riemann surface $\SR$ with prescribed heights of cylinders by considering the harmonic map from $\SR$ to the leaf space of the vertical foliation of $Φ$, thought of as a Riemannian graph. The novelty of the argument …

Random column sampling is not guaranteed to yield data sketches that preserve the underlying structures of the data and may not sample sufficiently from less-populated data clusters. Also, adaptive sampling can often provide accurate low rank approximations, yet may fall short of producing descriptive data sketches, es…

This is the first paper of a series in which we plan to study spectral asymptotics for sub-Riemannian Laplacians and to extend results that are classical in the Riemannian case concerning Weyl measures, quantum limits, quantum ergodicity, quasi-modes, trace formulae.Even if hypoelliptic operators have been well studied…

In this paper we introduce a simple approach for exploration in reinforcement learning (RL) that allows us to develop theoretically justified algorithms in the tabular case but that is also extendable to settings where function approximation is required. Our approach is based on the successor representation (SR), which…

Unified geometric formulation of Maxwell-Vlasov system using presymplectic and symmetry reduction.

SR-NAM maps low-res images to multiple high-res images realistically.

The study addresses overlooked data-generating processes in time-series asset pricing.

With the recent advancement in the deep learning technologies such as CNNs and GANs, there is significant improvement in the quality of the images reconstructed by deep learning based super-resolution (SR) techniques. In this work, we propose a robust loss function based on the preservation of edges obtained by the Can…

Robust Reinforcement Learning aims to derive optimal behavior that accounts for model uncertainty in dynamical systems. However, previous studies have shown that by considering the worst case scenario, robust policies can be overly conservative. Our soft-robust framework is an attempt to overcome this issue. In this pa…

A hybrid algorithm combines optimization and enumeration for symbolic regression.

Local Sasaki-Ricci solitons are $η$-Einstein in certain fiber products of homogeneous Sasakian manifolds.

The paper proposes using network science to improve portfolio optimization by reducing noise in covariance estimation.

We study the geodesics problem in Heisenberg group H (case SR and riemannian). The sheaf of infinitesimal automorphisms of the (2n,2n+1) distribution D over H is an infinite, transitive Lie algebra sheaf.

New findings show increased exploration needed in non-stationary RL tasks.

Here we propose using the successor representation (SR) to accelerate learning in a constructive knowledge system based on general value functions (GVFs). In real-world settings like robotics for unstructured and dynamic environments, it is infeasible to model all meaningful aspects of a system and its environment by h…

DeepSupp detects financial support levels using attention mechanisms.

Despite excellent progress in recent years, mode collapse remains a major unsolved problem in generative adversarial networks (GANs).In this paper, we present spectral regularization for GANs (SR-GANs), a new and robust method for combating the mode collapse problem in GANs. Theoretical analysis shows that the optimal …

In this paper, we consider signal detection algorithms in a multiple-input multiple-output (MIMO) decode-forward (DF) relay channel with one source, one relay, and one destination. The existing suboptimal near maximum likelihood (NML) detector and the NML with two-level pair-wise error probability (NMLw2PEP) detector a…