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.
Contextualizing financial news improves stock price predictions.
A new approach learns to represent context for nonstationary bandits.
New algorithm reduces online learning regret by exploiting historical invariances.
The paper develops a new framework for detecting distributional drifts conditioned on context.
This article offers an introductory look at Khovanov homology and its historical context.
Proposes a new fairness definition based on equity for machine learning classification.
Spotify improves content mix using contextual bandits.
The paper explores using historical data to improve clinical trial analysis by optimizing covariate weights.
The performance of machine learning model can be further improved if contextual cues are provided as input along with base features that are directly related to an inference task. In offline learning, one can inspect historical training data to identify contextual clusters either through feature clustering, or hand-cra…
In this paper we present some new results on the tautness of Riemannian foliations in their historical context. The first part of the paper gives a short history of the problem. For a closed manifold, the tautness of a Riemannian foliation can be characterized cohomologically. We extend this cohomological characterizat…
Knot Theory is currently a very broad field. Even a long survey can only cover a narrow area. Here we concentrate on the path from Goeritz matrices to quasi-alternating links. On the way, we often stray from the main road and tell related stories, especially if they allow as to place the main topic in a historical cont…
When learning from a batch of logged bandit feedback, the discrepancy between the policy to be learned and the off-policy training data imposes statistical and computational challenges. Unlike classical supervised learning and online learning settings, in batch contextual bandit learning, one only has access to a colle…
Algorithm improves decision-making with partially observed contexts using pretrained models.
Bayesian framework improves variance component estimation in MET data.
AI2V learns user representations by focusing on recent interests.
Benchmark assesses forecasting models' ability to use textual context.
New method interprets machine learning forecasts as historical analogies.
Study examines ETFs for Pakistan exposure, highlighting risks and performance.
Proponents of behavioral finance have identified several "puzzles" in the market that are inconsistent with rational finance theory. One such puzzle is the "excess volatility puzzle". Changes in equity prices are too large given changes in the fundamentals that are expected to change equity prices. In this paper, we of…
Paper tackles overfitting in RL for trade execution.
AutoML aims to automate machine learning tasks, reviewed in this chapter.
Machine learning identifies types of alterations in historical manuscripts.
We revisit the problem of pricing options with historical volatility estimators. We do this in the context of a generalized GARCH model with multiple time scales and asymmetry. It is argued that the reason for the observed volatility risk premium is tail risk aversion. We parametrize such risk aversion in terms of thre…
Novel method for nowcasting implied volatility using neural operators.
This article attempts to delineate the roles played by non-dynamical background structures and Killing symmetries in the construction of stress-energy-momentum tensors generated from a diffeomorphism invariant action density. An intrinsic coordinate independent approach puts into perspective a number of spurious argume…
Improved crypto market forecasting using historical price reactions to tweets.
A novel algorithm for actively trading stocks is presented. While traditional expert advice and "universal" algorithms (as well as standard technical trading heuristics) attempt to predict winners or trends, our approach relies on predictable statistical relations between all pairs of stocks in the market. Our empirica…
Enhanced financial trading system using multi-agent LLMs with layered memory.
Author discusses the Poincaré conjecture from 40 years ago.
AI mirrors modern math's autonomous development, raising interpretive challenges.
Next basket recommendation, which aims to predict the next a few items that a user most probably purchases given his historical transactions, plays a vital role in market basket analysis. From the viewpoint of item, an item could be purchased by different users together with different items, for different reasons. Ther…
This paper investigates the impact of pre-existing offline data on online learning, in the context of dynamic pricing. We study a single-product dynamic pricing problem over a selling horizon of periods. The demand in each period is determined by the price of the product according to a linear demand model with unkn…
Unified HS and related methods with explicit modeling assumptions.
Algorithmic risk assessments are increasingly used to help humans make decisions in high-stakes settings, such as medicine, criminal justice and education. In each of these cases, the purpose of the risk assessment tool is to inform actions, such as medical treatments or release conditions, often with the aim of reduci…
We propose a Markov chain model for credit rating changes. We do not use any distributional assumptions on the asset values of the rated companies but directly model the rating transitions process. The parameters of the model are estimated by a maximum likelihood approach using historical rating transitions and heurist…
This article attempts to place the emergence of probabilistic numerics as a mathematical-statistical research field within its historical context and to explore how its gradual development can be related both to applications and to a modern formal treatment. We highlight in particular the parallel contributions of Sul'…
Framework detects anomalies in industrial processes using deep learning.
The link between different psychophysiological measures during emotion episodes is not well understood. To analyse the functional relationship between electroencephalography (EEG) and facial electromyography (EMG), we apply historical function-on-function regression models to EEG and EMG data that were simultaneously r…
A pedagogical but concise overview of fiber bundles and their connections is provided, in the context of gauge theories in physics. The emphasis is on defining and visualizing concepts and relationships between them, as well as listing common confusions, alternative notations and jargon, and relevant facts and theorems…
ArtificialReplay improves data efficiency in bandits using historical data.
The paper explores Wiener-Granger causality and its computational enhancements.
Paper establishes MLE consistency for market microstructure models.
ADR helps LLMs find and use historical analogies for foresight analysis.
Word meaning changes over time, depending on linguistic and extra-linguistic factors. Associating a word's correct meaning in its historical context is a central challenge in diachronic research, and is relevant to a range of NLP tasks, including information retrieval and semantic search in historical texts. Bayesian m…
The use of machine learning systems to support decision making in healthcare raises questions as to what extent these systems may introduce or exacerbate disparities in care for historically underrepresented and mistreated groups, due to biases implicitly embedded in observational data in electronic health records. To …
Proposes DeepSDRF for continuous treatment recommendation from clinical survival data.
Proposes dynamic borrowing method for historical data in clinical trials.
In machine learning we often try to optimise a decision rule that would have worked well over a historical dataset; this is the so called empirical risk minimisation principle. In the context of learning from recommender system logs, applying this principle becomes a problem because we do not have available the reward …