Research
On-device research index

arXiv research

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.

169,181 papers · 148 categories

Trend · papers per month

2.7%5.5%8.2%11.0% · May 202619922001200920182026
48 results for premise selection

ATPboost uses ATP feedback for binary premise selection in large-theory problem solving.

problem Learning relevant premises for ATP-based theorem proving in binary classification.
method Binary classification using XGBoost, with negative examples generated from alternative proofs.
result ATPboost outperforms k-nearest neighbors in binary premise selection.

New method selects facts in proofs using stateful recurrent neural networks.

problem Selecting facts for proving new goals over large formal libraries.
method Stateful architecture based on recurrent neural networks with data augmentation.
result Significantly better performance and solving many new problems compared to previous methods.

Automated theorem proving without imitation, using tf-idf for premise selection.

problem Automated theorem proving in large knowledge bases without human guidance.
method Exploration mechanism mixing tf-idf selected premises in a deep reinforcement learning context.
result The prover trained with this approach outperforms provers trained only on human proofs.

LeanDojo removes barriers to theorem proving with open-source tools and data.

problem Difficulty in reproducing and building on existing theorem proving methods.
method Introduces LeanDojo, an open-source Lean playground with toolkits, data, models, and benchmarks.
result ReProver, an LLM-based prover augmented with retrieval, outperforms non-retrieval baselines and GPT-4.

Semi-supervised learning improves classification in high dimensions.

problem Combining labeled and unlabeled data for high-dimensional classification.
method Information theoretic and computational lower bounds analysis for feature selection.
result Semi-supervised learning is advantageous for classification in high dimensions.

The study examines how language models learn to represent the world, identifying conditions for ecological veridicality.

problem Understanding when language models learn to represent the world accurately and how this learning process can fail.
method Analyzes the Bayes-optimal next-token cross-entropy decomposition and the role of training ecology in shaping model representations.
result The minimum-complexity zero-excess solution is the quotient partition by training equivalence, and this solution is not preserved in in-context learning or per-task adaptation.

Comment refutes the deconfounder method's premise about ignorability.

problem The deconfounder method's premise about ignorability is incorrect.
method The deconfounder method proposes a variable making multiple causes conditionally independent controls for unmeasured multi-cause confounding.
result No fact about observed data alone can be informative about ignorability.

REALFIN benchmarks financial reasoning by removing implicit assumptions, revealing model weaknesses.

problem Models struggle when implicit assumptions are missing, leading to incorrect answers.
method Developed a bilingual benchmark that systematically removes essential premises from financial questions.
result General-purpose models over-commit, while finance-specialized models fail to identify missing premises.

Any surface can be foliated into equipotential hypersurfaces of the level sets. A current result is that the contours are the progressing wave fronts of a certain hyperbolic partial differential equation, a wave equation. It is connected with the gradient lines, as well as with a corresponding eikonal equation. The lev…

2013-09-12abs ↗pdf ↗

The isotropic correlation model explains equity returns better than linear factor models.

problem Understanding the covariance structure of equity returns.
method Developed an isotropic covariance model for equity returns, analyzed empirical data, and compared results to linear factor models.
result The isotropic covariance model provides a better fit to recent equity return data compared to linear factor models.

PSC classifier improves HDLSS classification on class-imbalanced data.

problem Classification on high-dimension low-sample-size data with class imbalance.
method Population Structure-learned Classifier (PSC) maximizing inter-class and intra-class scatter matrices.
result PSC outperforms state-of-the-art methods on IHDLSS.

It is known that the impact of transactions on stock price (market impact) is a concave function of the size of the order, but there exists little quantitative theory that suggests why this is so. I develop a quantitative theory for the market impact of hidden orders (orders that reflect the true intention of buying an…

2008-04-24abs ↗pdf ↗

Study uses FDA to analyze discount functions of different temperaments.

problem Traditional finance models fail to capture individual differences in investment choices.
method Functional Data Analysis (FDA) to investigate temporal discounting behaviors.
result Heterogeneity within each temperament revealed, suggesting diverse investor profiles.

New method improves bivariate causal discovery by accurately estimating cause variable complexity.

problem Improper estimation of cause variable complexity in current MDL-based methods.
method Rate-distortion MDL (RDMDL) using information dimension for cause variable complexity estimation.
result RDMDL achieves competitive performance on Tübingen dataset.

Lean Copilot uses LLMs to assist theorem proving in Lean, improving efficiency and automation.

problem Challenges in using existing neural theorem provers to prove novel theorems autonomously.
method Introduces Lean Copilot, a framework for integrating LLMs into Lean's theorem proving process.
result Lean Copilot automates 74.2% of proof steps on average, significantly improving over existing methods.

Develops a new method for summarizing ranking data using bucket orders.

problem Summarizing ranking data without a vector space structure.
method Introduces a mass transportation metric to quantify bucket representations and selects optimal bucket orders.
result Optimal bucket orders minimize empirical distortion and provide sparse representations of ranking distributions.

This paper proposes a generalization bound for GAN-synthetic data.

problem Improving classification accuracy and privacy in supervised learning.
method Proposes a generalization bound to measure the gap between synthetic and real data.
result Guarantees the generalization capability of classifiers learning from GAN-synthetic data.

Two oppositely charged droplets of (say) water in e.g. oil or air will tend to drift together under the influence of their charges. As they make contact, one might expect them to coalesce and form one large droplet, and this indeed happens when the charge difference is sufficiently small. However, Ristenpart et al disc…

2013-02-20abs ↗pdf ↗

Designed to compete with fiat currencies, bitcoin proposes it is a crypto-currency alternative. Bitcoin makes a number of false claims, including: solving the double-spending problem is a good thing; bitcoin can be a reserve currency for banking; hoarding equals saving, and that we should believe bitcoin can expand by …

2013-12-07abs ↗pdf ↗

Standard acquisition functions are sufficient for asynchronous Bayesian optimization.

problem Redundant and repeated queries in asynchronous Bayesian optimization.
method Conceptual analysis and theoretical guarantees of standard acquisitions.
result Standard acquisition functions achieve theoretical guarantees equivalent to Thompson sampling in asynchronous settings.

Partial-input models fail to detect dataset artifacts, even when they perform poorly.

problem The effectiveness of partial-input models in detecting dataset artifacts is questionable.
method Design artificial datasets and identify trivial patterns in the SNLI dataset.
result Partial-input models can solve examples previously considered hard, indicating potential dataset artifacts.

We show that conically smooth stratified spaces embed fully faithfully into \infty-categories. This articulates a stratified generalization of the homotopy hypothesis proposed by Grothendieck. As such, each \infty-category defines a stack on conically smooth stratified spaces, and we identify the descent conditions…

2015-02-05abs ↗pdf ↗

Paper develops a new model for predicting volatility surface.

problem Predicting volatility in financial markets is challenging due to its non-observable nature and complex dynamics.
method Physics-informed convolutional transformer architecture.
result The new model outperforms other deep-learning architectures in predicting volatility surface.

Much recent machine learning research has been directed towards leveraging shared statistics among labels, instances and data views, commonly referred to as multi-label, multi-instance and multi-view learning. The underlying premises are that there exist correlations among input parts and among output targets, and the …

2017-02-22abs ↗pdf ↗

This paper introduces C-DSL to improve data mining outcomes by considering context.

problem Data collection ambiguities, data imbalance, hidden biases, lack of domain info, and data incompleteness.
method Developed Context-Driven Data Science Lifecycle (C-DSL) to address data quality issues.
result Tangible improvements to data mining outcomes were achieved through C-DSL.

Detecting emergence of a low-rank signal from high-dimensional data is an important problem arising from many applications such as camera surveillance and swarm monitoring using sensors. We consider a procedure based on the largest eigenvalue of the sample covariance matrix over a sliding window to detect the change. T…

2016-10-03abs ↗pdf ↗

A new method combines federated learning and logistic regression for better credit scoring.

problem Improving credit scoring models while protecting data privacy.
method Projected gradient-based vertical federated learning (FL-LRBC) for logistic regression.
result Significant improvement in AUC and KS statistics due to data enrichment.

The paper values reinsurance contracts for dynamic catastrophe claims without arbitrage.

problem Valuation of reinsurance contracts for dynamic catastrophe claims without arbitrage.
method Compound dynamic contagion process, Esscher transform, Monte Carlo simulation.
result Arbitrage-free premiums for catastrophe stop-loss reinsurance contracts.

In topic modeling, many algorithms that guarantee identifiability of the topics have been developed under the premise that there exist anchor words -- i.e., words that only appear (with positive probability) in one topic. Follow-up work has resorted to three or higher-order statistics of the data corpus to relax the an…

2016-11-15abs ↗pdf ↗

New method reduces bias in NLI models using ensemble adversarial training.

problem Spurious correlations between hypotheses and entailment classes in NLI datasets.
method Adversarial training with an ensemble of classifiers to reduce bias in sentence representations.
result Ensemble adversarial training produces more robust NLI models, outperforming previous methods.

Trust-aware MAB improves learning performance by accounting for human deviation.

problem Learning performance suffers when humans deviate from recommended policies due to lack of trust.
method Integrates a dynamic trust model into MAB framework, establishing minimax regret and proposing a two-stage trust-aware procedure.
result Proves near-optimal statistical guarantees for trust-aware MAB algorithms.

FLFE improves machine learning by efficiently and securely transforming features.

problem Efficiently and securely transforming features in a multi-party setting.
method FLFE uses a pre-learning pattern to selectively transform features, reducing communication overhead.
result FLFE outperforms evaluation-based approaches in feature transformation efficiency.