LLMs struggle with arithmetic tasks unless they use high numerical precision.
problem Improving arithmetical reasoning capabilities of LLMs.
method Theoretical analysis and empirical experiments on numerical precision.
result LLMs require high numerical precision to efficiently handle arithmetic tasks.
Agent Trading Arena trains LLMs in real-time financial markets to improve numerical reasoning.
problem Limited real-world training for LLMs in financial markets.
method Virtual zero-sum stock market with competitive multi-agent trading.
result LLMs perform better with chart-based visualizations and a reflection module.
FinTradeBench benchmarks LLMs for financial reasoning combining company fundamentals and market signals.
problem Challenges in evaluating financial reasoning models for LLMs.
method Developed a benchmark integrating company fundamentals and trading signals, using a calibration-then-scaling framework.
result Clear performance gap between LLMs, retrieval improves reasoning over textual fundamentals but not trading signals.
Neural networks currently dominate the machine learning community and they do so for good reasons. Their accuracy on complex tasks such as image classification is unrivaled at the moment and with recent improvements they are reasonably easy to train. Nevertheless, neural networks are lacking robustness and interpretabi…
We present a stochastic numerical method for solving fully non-linear free boundary problems of parabolic type and provide a rate of convergence under reasonable conditions on the non-linearity.
Survey of neurosymbolic AI methods for reasoning over knowledge graphs.
problem Combining symbolic reasoning with deep learning for graph data.
method Logically-informed embedding, embedding with logical constraints, and rule learning approaches.
result A novel taxonomy for classifying neurosymbolic reasoning methods on knowledge graphs.
Study shows GPT's earnings forecasts are human-like but not always accurate.
problem Information friction in AI-generated financial analysis.
method Examined GPT's earnings forecasts following corporate earnings releases and proposed a diagnostic framework.
result GPT's narrative attention is consistent and human-like but not always associated with higher forecast accuracy.
Kernel smoothing improves LLM reasoning efficiency.
problem Efficiently estimate value functions with limited samples for reinforcement learning.
method Kernelized advantage estimation using classical nonparametric statistics.
result Improved policy optimization with accurate value and gradient estimation.
Alpha-R1 uses LLMs to reason about economic factors and news for better alpha screening.
problem Challenges in data-driven investment strategies due to signal decay and regime shifts.
method Reinforcement learning trained on 8B parameters to evaluate alpha relevance under changing market conditions.
result Empirically outperforms benchmark strategies and shows improved robustness to alpha decay.
New approach to counterfactual reasoning avoids demographic interventions.
problem Limitations of traditional counterfactual reasoning in AI systems.
method Backtracking counterfactual approach instead of interventional.
result Allows addressing social concerns without demographic interventions.
For a number of reasons, computational intelligence and machine learning methods have been largely dismissed by the professional community. The reasons for this are numerous and varied, but inevitably amongst the reasons given is that the systems designed often do not perform as expected by their designers. The reasons…
Transformers solve parity problems efficiently with step-by-step reasoning.
problem Training transformers to solve complex, recursive problems like parity.
method Training a one-layer transformer to solve k-parity, incorporating intermediate parities into the loss function, and using teacher forcing or augmented data. result Transformers can learn parity in one gradient update with intermediate supervision or self-consistency checks.
Non-parametric time series forecasting without assuming a specific distribution.
problem Time series forecasting with numerical stability issues in classical models.
method Generates predictions by sampling from the empirical distribution of time series data.
result The proposed method produces reasonable forecasts without numerical stability issues.
Study validates numerical method for singular FBSDEs convergence.
problem Solving singular FBSDEs and associated PDEs.
method Particles approximation for transport operator and tree approximation for diffusion operator.
result Convergence rate of numerical method proved under reasonable conditions.
New method explains anomalies in multivariate time series data.
problem Understanding and explaining anomalies in multivariate time series data.
method Counterfactual reasoning applied to MDI-detected anomalous intervals.
result Our method accurately identifies and explains anomalies in various extreme events.
Method detects errors in numerical data using regression models.
problem Noise and errors in numerical datasets.
method Introduced veracity scores and a filtering procedure for error detection.
result Method outperforms other approaches in identifying incorrect values.
In this paper we study the deformations of bihamiltonian PDEs of hydrodynamic type with one dependent variable. The reason we study such deformations is that the deformed systems maintain an infinite number of commuting integrals of motion up to a certain order in the deformation parameter. This fact suggests that thes…
In this short note, we consider mean-variance optimized portfolios with transaction costs. We show that introducing quadratic transaction costs makes the optimization problem more difficult than using linear transaction costs. The reason lies in the specification of the budget constraint, which is no longer linear. We …
The memory capacity of linear echo state networks is accurately calculated using new numerical methods.
problem Numerical evaluations of memory capacity in recurrent neural networks often contradict theoretical bounds.
method Developed robust numerical approaches exploiting MC neutrality with respect to the input mask matrix.
result Memory curves fully agree with theory when using the proposed methods.
Improves many-shot learning by optimizing and generating influential examples.
problem Limited performance in many-shot in-context learning (ICL).
method Iterative optimization and generation of influential examples.
result Significant improvements across various tasks using BRIDGE.
In this paper, we treat the problem of evaluating the asymptotic error in a numerical integration scheme as one with inherent uncertainty. Adding to the growing field of probabilistic numerics, we show that Gaussian process regression (GPR) can be embedded into a numerical integration scheme to allow for (i) robust sel…
Paper cleans option price datasets by removing outliers.
problem Unusual option prices in datasets.
method Statistical techniques to identify and remove outliers.
result Removes option prices violating no arbitrage assumption.
This work analyzes CoT prompting methods from a statistical estimation perspective.
problem Improving the effectiveness of LLMs in solving multi-step reasoning problems.
method Introducing a multi-step latent variable model to characterize CoT prompting from a statistical estimation viewpoint.
result The CoT estimator is equivalent to a Bayesian estimator when the pretraining dataset is large.
Machine learning models predict the behavior of negatively buoyant jets from wastewater.
problem Minimizing harmful effects of negatively buoyant jets during wastewater discharge.
method Training machine learning models (ANN, XGBoost, CatBoost, LightGBM) on OpenFOAM simulations and experimental data.
result Artificial Neural Network provided the best prediction with R2 0.98 and RMSE 0.28.
Erdős introduced the noncommuting graph, in order to study the number of commuting elements in a finite group. Despite the use of combinatorial ideas, his methods involved several techniques of classical analysis. The interest for this graph is becoming relevant in the last years for various reasons. Here we deal with …
The power of neural networks lies in their ability to generalize to unseen data, yet the underlying reasons for this phenomenon remain elusive. Numerous rigorous attempts have been made to explain generalization, but available bounds are still quite loose, and analysis does not always lead to true understanding. The go…
The paper offers a unified approach to the study of three locally adaptive estimation methods in the context of univariate time series from both theoretical and empirical points of view. A general procedure for the computation of critical values is given. The underlying model encompasses all distributions from the expo…
The wavelet Maximum Entropy on the Mean (wMEM) approach to the MEG inverse problem is revisited and extended to infer brain activity from full space-time data. The resulting dimensionality increase is tackled using a collection of techniques , that includes time and space dimension reduction (using respectively wavelet…
In this paper the multivariate fractional trading ansatz of money management from Ralph Vince (Portfolio Management Formulas: Mathematical Trading Methods for the Futures, Options, and Stock Markets, John Wiley & Sons, Inc., 1990) is discussed. In particular, we prove existence and uniqueness of an optimal f of the res…
LaTRO optimizes latent reasoning in LLMs without external reward.
problem Training LLMs to perform complex reasoning tasks.
method Formulates reasoning as latent distribution sampling and optimizes via variational approaches.
result LLMs improve reasoning and evaluation quality through self-improvement.
A major drawback of the Standard Heston model is that its implied volatility surface does not produce a steep enough smile when looking at short maturities. For that reason, we introduce the Stationary Heston model where we replace the deterministic initial condition of the volatility by its invariant measure and show,…
Auto-CEI improves LLM reasoning by balancing assertiveness and conservativeness.
problem Hallucinations and laziness in LLM reasoning tasks.
method Expert Iteration explores reasoning trajectories, guiding incorrect paths back on track and promoting appropriate 'I don't know' responses.
result Auto-CEI achieves superior alignment in logical reasoning, mathematics, and planning tasks.
A framework isolates VQA reasoning from perception for better model evaluation.
problem Improper separation of visual perception and reasoning in VQA models.
method Introducing a framework and a top-down calibration technique to decouple reasoning from perception.
result Improved evaluation of VQA models by separating reasoning from perception.
Probabilistic solvers improve stability for stiff systems.
problem Performance penalties for small steps in stiff systems.
method Probabilistic exponential integrators that include fast linear dynamics in the prior.
result Proven L-stability and probabilistic error accounting.
Method extracts governing laws from non-Gaussian stochastic systems data.
problem Modeling complex dynamics with non-Gaussian Lévy noise.
method Data-driven method to extract stochastic dynamical systems from noisy data.
result Established a theoretical framework and numerical algorithm to compute Lévy jump measure, drift, and diffusion.
CyPhERS provides real-time event info for CPSs, avoiding downtime.
problem Real-time event identification in CPSs is challenging due to complex interdependencies and rare events.
method CyPhERS integrates cyber and physical components, generating event signatures for known and unknown events.
result Event signatures provide relevant and inferable information on both known and unknown event types.
A new method for math reasoning that allows for iterative correction.
problem Standard reasoning models commit to each token and cannot recover from early errors.
method Generative framework with latent thought vectors for iterative self-correction.
result 30 rethinking iterations surpass baselines with 15 times more parameters.
This paper considers the single factor Heath-Jarrow-Morton model for the interest rate curve with stochastic volatility. Its natural formulation, described in terms of stochastic differential equations, is solved through Monte Carlo simulations, that usually involve rather large computation time, inefficient from a pra…
Inferring new facts from existing knowledge graphs (KG) with explainable reasoning processes is a significant problem and has received much attention recently. However, few studies have focused on relation types unseen in the original KG, given only one or a few instances for training. To bridge this gap, we propose Co…
LLM4Causal democratizes causal reasoning via fine-tuned LLMs.
problem Limited capability of LLMs in causal inference and interpretation.
method Fine-tuning an open-source LLM for causal tasks, proposing datasets for instruction tuning.
result LLM4Causal delivers end-to-end solutions for causal problems and interprets results easily.
Transformers learn multi-step reasoning through gradient descent.
problem Understanding how transformers solve symbolic multi-step reasoning tasks.
method Theoretical analysis of gradient descent dynamics and multi-phase training.
result Trained one-layer transformers can solve both backward and forward reasoning tasks with generalization guarantees.
Transformers with CoT don't enhance reasoning power across all tasks.
problem Does CoT enhance the reasoning power of transformers?
method Examined the memorization capabilities of fixed-precision transformers with and without CoT.
result Transformers with CoT cannot memorize all reasoning tasks, leading to a negative answer.
Pattern analysis often requires a pre-processing stage for extracting or selecting features in order to help the classification, prediction, or clustering stage discriminate or represent the data in a better way. The reason for this requirement is that the raw data are complex and difficult to process without extractin…
Early stopping methods reduce unnecessary reasoning steps in LLMs by monitoring uncertainty signals.
problem LLMs sometimes generate unnecessary reasoning steps, especially under uncertainty.
method Statistically principled early stopping methods that monitor uncertainty signals during generation.
result Uncertainty-aware early stopping improves efficiency and reliability in LLM reasoning, especially in math reasoning.
Achieving artificial visual reasoning - the ability to answer image-related questions which require a multi-step, high-level process - is an important step towards artificial general intelligence. This multi-modal task requires learning a question-dependent, structured reasoning process over images from language. Stand…
Hybrid framework injects TSLM insights into GRLM for robust time-series reasoning.
problem Lack of domain-specific knowledge in large language models for time-series reasoning.
method Hybrid knowledge-injection framework combining RLVR for efficient knowledge transfer.
result Consistently outperforms existing models by 7.9%-26.1% on multivariate time-series benchmarks.
Neural Logic Reasoning integrates deep learning and symbolic logic for better prediction tasks.
problem Lack of cognitive reasoning in deep neural networks limits their ability to solve complex prediction tasks.
method Proposes Logic-Integrated Neural Network (LINN) that learns logical operations and conducts propositional logical reasoning.
result LINN significantly outperforms state-of-the-art recommendation models in Top-K recommendation.
Forward-prediction models enhance physical reasoning, but only for specific tasks.
problem Improving physical reasoning in complex tasks involving many objects.
method Incorporated forward-prediction models into simple physical-reasoning agents and evaluated their performance on the PHYRE benchmark.
result Forward-prediction models improve physical-reasoning performance, especially on complex tasks, but generalization to new task templates is challenging.