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.
New methods improve LLM preference optimization by intelligently weighting multiple reference models.
This paper solves the multiple reference model problem in RLHF with exact solutions and sample complexity guarantees.
This paper uses reference priors to improve deep learning models with unlabeled and labeled data.
Benchmark evaluates financial misinformation detection models, revealing weaknesses without external context.
Informative Bayesian priors are often difficult to elicit, and when this is the case, modelers usually turn to noninformative or objective priors. However, objective priors such as the Jeffreys and reference priors are not tractable to derive for many models of interest. We address this issue by proposing techniques fo…
This paper improves model training by using a reference model to guide target model training.
This paper introduces a relative model risk measure of a product priced with a given model, with respect to another reference model for which the market is assumed to be driven. This measure allows comparing products valued with different models (pricing hypothesis) under a homogeneous framework which allows concluding…
The paper introduces a method for forecasting corporate sales growth using multiple reference variables.
Active-GRPO improves molecular optimization by actively deciding when to imitate or self-improve.
Auto-regressive sequence-to-sequence models with attention mechanism have achieved state-of-the-art performance in many tasks such as machine translation and speech synthesis. These models can be difficult to train. The standard approach, teacher forcing, guides a model with reference output history during training. Th…
This article proposes a biologically inspired neurocomputational architecture which learns associations between words and referents in different contexts, considering evidence collected from the literature of Psycholinguistics and Neurolinguistics. The multi-layered architecture takes as input raw images of objects (re…
Enhances anomaly detection using multiple reference datasets.
RB-Modulation trains free diffusion models without external adapters.
HalluWorld benchmarks hallucinations in language models across diverse tasks.
Synthetic reference strings are as effective as real ones for training citation parsing models.
Optimal order execution strategies for brokers under reference benchmarks.
Choosing a reference group in Oaxaca-Blinder decomposition can reverse conclusions.
Recent research in psycholinguistics has provided increasing evidence that humans predict upcoming content. Prediction also affects perception and might be a key to robustness in human language processing. In this paper, we investigate the factors that affect human prediction by building a computational model that can …
New method detects if data points were used in training models with low cost and high power.
Modeling consumption and investment decisions with reference point and drawdown constraints.
Method learns neural network to overestimate reference function with guarantees.
Study asset pricing with reference-dependent preferences, finding matching equity premia.
Methods for learning to search for structured prediction typically imitate a reference policy, with existing theoretical guarantees demonstrating low regret compared to that reference. This is unsatisfactory in many applications where the reference policy is suboptimal and the goal of learning is to improve upon it. Ca…
A new method samples from multi-modal distributions without hyperparameter tuning.
Study shows mutual funds add little value for uninformed investors.
This paper develops a model of reference-dependent assessment of subjective beliefs in which loss-averse people optimally choose the expectation as the reference point to balance the current felicity from the optimistic anticipation and the future disappointment from the realisation. The choice of over-optimism or over…
We present a weakly-supervised data augmentation approach to improve Named Entity Recognition (NER) in a challenging domain: extracting biomedical entities (e.g., proteins) from the scientific literature. First, we train a neural NER (NNER) model over a small seed of fully-labeled examples. Second, we use a reference s…
Probabilistic generative models provide a powerful framework for representing data that avoids the expense of manual annotation typically needed by discriminative approaches. Model selection in this generative setting can be challenging, however, particularly when likelihoods are not easily accessible. To address this …
Reference metrics are used to define the differential structure on multicube representations of manifolds, i.e., they provide a simple and practical way to define what it means globally for tensor fields and their derivatives to be continuous. This paper introduces a general procedure for constructing reference metrics…
This paper improves indoor positioning accuracy by deploying reference nodes to ensure Line-of-Sight.
A salient approach to interpretable machine learning is to restrict modeling to simple models. In the Bayesian framework, this can be pursued by restricting the model structure and prior to favor interpretable models. Fundamentally, however, interpretability is about users' preferences, not the data generation mechanis…
For a product of interest, we propose a search method to surface a set of reference products. The reference products can be used as candidates to support downstream modeling tasks and business applications. The search method consists of product representation learning and fingerprint-type vector searching. The product …
Current multi-reference style transfer models for Text-to-Speech (TTS) perform sub-optimally on disjoints datasets, where one dataset contains only a single style class for one of the style dimensions. These models generally fail to produce style transfer for the dimension that is underrepresented in the dataset. In th…
This paper develops a method to select a reference contract for multi-contract quoting to minimize execution risk.
New method generates synthetic time series paths with more flexibility.
The paper analyzes how conformal prediction works with contaminated reference data.
This article considers the quasi-local conserved quantities with respect to a reference spacetime with a cosmological constant. We follow the approach developed by the authors in [25,26,7] and define the quasi-local energy as differences of surface Hamiltonians. The ground state for the gravitational energy is taken to…
Leveraging reference-only samples for two-sample testing under size asymmetry
In this paper the introduction of notion of reference vector paves the way for a combination of classical and social approaches in the framework of referential preferences given by matrix groups. It is shown that individual demand issue from rational decision does not depend on that reference.
The paper analyzes the reward improvement of aligned policies in large language models.
Paper proposes using LSTM for LSH-based sequence alignment.
This work extends entropic optimal transport to non-product reference couplings, focusing on Gaussian cases.
Study validates ML-UQ calibration statistics using simulated reference values.
Investor finds a fair outcome in complex financial markets.
This paper describes a reference architecture for self-maintaining systems that can learn continually, as data arrives. In environments where data evolves, we need architectures that manage Machine Learning (ML) models in production, adapt to shifting data distributions, cope with outliers, retrain when necessary, and …
The purpose of this paper is to discuss how topology and geometry provide, in many instances, the connective tissue that enables logical comprehension. We illustrate this theme with many examples including Venn diagrams, knot diagrams, knot-logical diagrams and an arrow of reference that elucidates self-reference and G…
Despite some empirical success at correcting exposure bias in machine translation, scheduled sampling algorithms suffer from a major drawback: they incorrectly assume that words in the reference translations and in sampled sequences are aligned at each time step. Our new differentiable sampling algorithm addresses this…
The exploitation of large-scale population data has the potential to improve healthcare by discovering and understanding patterns and trends within this data. To enable high throughput analysis of cardiac imaging data automatically, a pipeline should comprise quality monitoring of the input images, segmentation of the …