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.
Negative step sizes improve second-order methods for neural networks.
Bayesian method mitigates negative transfer in unknown source data.
Social media reduces individual investors' disposition effect through negative information.
Improved visual representation learning with conditional negative sampling.
This paper tackles negative transfer in multi-task learning by introducing class-wise weights.
Negative user preference is an important context that is not sufficiently utilized by many existing recommender systems. This context is especially useful in scenarios where the cost of negative items is high for the users. In this work, we describe a new recommender algorithm that explicitly models negative user prefe…
New mutual information framework improves contrastive learning for vision tasks.
Paper tackles entity matching over multi-source data, optimizing alignment and mitigating negative transfer.
Although the word-popularity based negative sampler has shown superb performance in the skip-gram model, the theoretical motivation behind oversampling popular (non-observed) words as negative samples is still not well understood. In this paper, we start from an investigation of the gradient vanishing issue in the skip…
Improved estimation for imbalanced data using log odds correction and optimal sampling.
We use classical results in smoothing theory to extract information about the rational homotopy groups of the space of negatively curved metrics on a high dimensional manifold. It is also shown that smooth M-bundles over spheres equipped with fiberwise negatively curved metrics, represent elements of finite order in th…
Paper proposes robust risk measures for non-negative risks with partial information.
ChatGPT can summarize corporate disclosures more concisely and effectively, improving stock market reactions.
New unsupervised method selects hard negative samples for contrastive learning.
Paper proposes GSSNMF for legal document classification and topic modeling.
This work formulates a novel song recommender system as a matrix completion problem that benefits from collaborative filtering through Non-negative Matrix Factorization (NMF) and content-based filtering via total variation (TV) on graphs. The graphs encode both playlist proximity information and song similarity, using …
We introduce the concept of "negative bubbles" as the mirror image of standard financial bubbles, in which positive feedback mechanisms may lead to transient accelerating price falls. To model these negative bubbles, we adapt the Johansen-Ledoit-Sornette (JLS) model of rational expectation bubbles with a hazard rate de…
New framework analyzes why more negative samples improve self-supervised learning performance.
Generative model improves safety in self-driving simulators and human motion generation.
We consider a problem of grouping multiple graphs into several clusters using singular value thesholding and non-negative factorization. We derive a model selection information criterion to estimate the number of clusters. We demonstrate our approach using "Swimmer data set" as well as simulated data set, and compare i…
We study the problem of what causes prices to change. We define the mechanical impact of a trading order as the change in future prices in the absence of any future changes in decision making, and its it informational impact as the remainder of the total impact once mechanical impact is removed. We introduce a method o…
NegBio-VAE models neural spike counts with negative binomial distribution.
The paper analyzes phase transitions in transfer learning for perceptrons.
A simple strategy prevents negative transfer in transfer learning.
Model learns image-word associations from captions using contrastive learning.
When labeled data is scarce for a specific target task, transfer learning often offers an effective solution by utilizing data from a related source task. However, when transferring knowledge from a less related source, it may inversely hurt the target performance, a phenomenon known as negative transfer. Despite its p…
Paper proves global convergence of NCELM model.
Paper tackles continuous transfer learning with evolving target domains.
Study finds financial YouTube channel 3PROTV predicts stock market performance and sentiment changes.
Security, privacy, and fairness have become critical in the era of data science and machine learning. More and more we see that achieving universally secure, private, and fair systems is practically impossible. We have seen for example how generative adversarial networks can be used to learn about the expected private …
DCGD improves training of PINNs by adjusting gradients to avoid negative inner products.
In this article we use rate-distortion theory, a branch of information theory devoted to the problem of lossy compression, to shed light on an important problem in latent variable modeling of data: is there room to improve the model? One way to address this question is to find an upper bound on the probability (equival…
A new framework for robust transfer learning that avoids negative transfer in domains with unequal information.
A new method improves graph node embeddings by considering both nearby and distant node similarities.
Learning rates in stochastic neural network training are currently determined a priori to training, using expensive manual or automated iterative tuning. This study proposes gradient-only line searches to resolve the learning rate for neural network training algorithms. Stochastic sub-sampling during training decreases…
New confidence intervals improve treatment effect estimation in randomized experiments.
Latent factor models for Recommender Systems with implicit feedback typically treat unobserved user-item interactions (i.e. missing information) as negative feedback. This is frequently done either through negative sampling (point--wise loss) or with a ranking loss function (pair-- or list--wise estimation). Since a ze…
A new multi-label CPC method improves mutual information estimation and representation learning.
Efficient Bayesian variable selection for binomial and negative binomial data.
Graphs with non-negative Ollivier-Ricci curvature cannot be expanders.
We study asymptotically harmonic manifolds of negative curvature, without any cocompactness or homogeneity assumption. We show that asymptotic harmonicity provides a lot of information on the asymptotic geometry of these spaces: in particular, we determine the volume entropy, the spectrum and the relative densities of …
Firms disclosing positive earnings surprises are more likely to disclose ESG information.
A growing number of empirical studies suggest that negative advertising is effective in campaigning, while the mechanisms are rarely mentioned. With the scandal of Cambridge Analytica and Russian intervention behind the Brexit and the 2016 presidential election, people have become aware of the political ads on social m…
Given a negatively curved geodesic metric space M, we study the asymptotic penetration behaviour of geodesic lines of M in small neighbourhoods of closed geodesics and of other compact convex subsets of M. We define a spiraling spectrum which gives precise information on the asymptotic spiraling lengths of geodesic lin…
Geometric theory of projection heads in self-supervised learning.
Negative screening is one method to avoid interactions with inappropriate entities. For example, financial institutions keep investment exclusion lists of inappropriate firms that have environmental, social, and government (ESG) problems. They create their investment exclusion lists by gathering information from variou…
The paper proposes a method of financial time series forecasting taking into account the semantics of news. For the semantic analysis of financial news the sampling of negative and positive words in economic sense was formed based on Loughran McDonald Master Dictionary. The sampling included the words with high frequen…
Count data take on non-negative integer values and are challenging to properly analyze using standard linear-Gaussian methods such as linear regression and principal components analysis. Generalized linear models enable direct modeling of counts in a regression context using distributions such as the Poisson and negati…