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.

168,695 papers · 148 categories

Trend · papers per month

4999148197 · Jun 202019922001200920172026
48 results for model-internalized priors

LLMs struggle with zero-shot annotation tasks due to model-internalized priors.

problem Impact of model-internalized priors on LLM performance in zero-shot annotation tasks.
method Investigated three dimensions: familiarity, decision stickiness, and susceptibility to misaligned task definitions.
result Nearly two-thirds of zero-shot errors are resistant to correction, with a rescue rate of 34.8%. Definition-Specific Familiarity (DSF) shows a positive association with model performance.

EXAGREE selects a stakeholder-aligned model to reduce conflicting explanations in machine learning.

problem Conflicting explanations from different attribution methods limit the adoption of machine learning models in safety-critical domains.
method EXAGREE is a two-stage framework that selects a Stakeholder-Aligned Explanation Model (SAEM) from a set of similar-performing models, maximizing Stakeholder-Machine Agreement (SMA).
result EXAGREE achieves simultaneous gains in faithfulness, plausibility, and fairness over baselines while preserving task accuracy.

A new method generates natural-looking adversarial examples by bounding internal activation values.

problem Creating natural-looking adversarial examples that closely mimic the original input.
method Bounding internal activation values through a distribution quantile bound and polynomial barrier loss function.
result Our attack achieves similar success and confidence levels as state-of-the-art methods but with more natural-looking perturbations.

Over-parameterized models can memorize noisy labels and still generalize well, revealing a hidden structure.

problem Understanding how over-parameterized models can simultaneously memorize noisy labels and generalize well.
method Investigated through modular arithmetic tasks with label noise using two-layer neural networks.
result Over-parameterized models can achieve near-perfect test accuracy with 80% label noise by extracting an internal generalization structure.

Unified understanding of neural networks on group operations verified.

problem Understanding and verifying neural networks trained on group operations.
method Investigated one-hidden-layer neural networks trained on binary operation of finite groups, revealing structure and providing a compact proof of model performance.
result Verified explanation applies to a large fraction of networks trained on the symmetric group S5, providing a >=95% accuracy bound for 45% of models.

PRoFILE accurately estimates feature importance under distribution shifts.

problem Challenges in estimating feature importance under distribution shifts.
method PRoFILE uses a loss estimator trained with a causal objective to estimate feature importance.
result PRoFILE accurately estimates feature importance under complex distribution shifts.

Researchers apply concept-based explainability to EEG data.

problem Understanding the internal states of complex EEG transformer models.
method Concept Activation Vectors (CAVs) adapted for EEG data, using externally labeled datasets and anatomically defined concepts.
result Both approaches to concept formation yield valuable insights into EEG model representations.

Paper proposes a black-box technique to generate adversarial samples.

problem Robustness of Deep Neural Networks (DNNs) to adversarial samples.
method Black-box Momentum Iterative Fast Gradient Sign Method (BMI-FGSM) using Differential Evolution to approximate gradients.
result Achieves high success rates in generating adversarial samples and misclassification.

This research integrates attention into XAI frameworks for better model explanations.

problem Improving the interpretability of transformer models.
method Developed two novel explanation methods: Shapley value decomposition and token-level directional derivatives.
result Attention weights can be meaningfully incorporated into XAI frameworks, enhancing transformer explainability.

Trade is a fundamental pillar of economy and a form of social organization. Its empirical characterization at the worldwide scale is represented by the World Trade Web (WTW), the network built upon the trade relationships between the different countries. Several scientific studies have focused on the structural charact…

2012-01-10abs ↗pdf ↗

Data taggants verify dataset ownership without harming models or requiring model internals.

problem Verifying dataset ownership without harming models or requiring model internals.
method Using pairs of out-of-distribution samples and random labels as secret keys, subtly altering a dataset to detect models trained on it.
result Data taggants reliably detect models trained on the protected dataset with high confidence, without compromising validation accuracy.

JUCAL jointly calibrates aleatoric and epistemic uncertainties in classifier ensembles.

problem Misrepresentation of predictive uncertainty due to unbalanced aleatoric and epistemic uncertainties.
method Joint Uncertainty Calibration (JUCAL) that jointly calibrates two constants to weight and scale uncertainties.
result Significantly outperforms state-of-the-art calibration methods across various text classification tasks.

A new Weyl prior is proposed for Bayesian statistics, offering a more canonical choice for parameter α.

problem Choosing a prior distribution for Bayesian inference.
method Proposed a new Weyl prior based on the Weyl structure on a statistical manifold.
result The Weyl prior is a special case of the α-parallel prior with α = -n, where n is the dimension of the statistical manifold.

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…

2017-04-04abs ↗pdf ↗

While Bayesian methods are praised for their ability to incorporate useful prior knowledge, in practice, convenient priors that allow for computationally cheap or tractable inference are commonly used. In this paper, we investigate the following question: for a given model, is it possible to compute an inference result…

2016-06-02abs ↗pdf ↗

Researchers derive exact priors for finite Bayesian neural networks.

problem Understanding non-Gaussian priors in finite Bayesian neural networks.
method Analytical derivation of function space priors for finite fully-connected feedforward networks.
result Exact solutions for priors of finite networks, including Meijer G-function for linear networks and mixtures for ReLU networks.

PRCD-MAP learns to trust imperfect priors in causal discovery, improving accuracy and robustness.

problem Tackles the brittle trade-off between blind trust and rejection of external priors in causal discovery.
method Proposes PRCD-MAP, a soft prior-consumption layer that assigns per-edge trust to imperfect priors and modulates regularization in a MAP objective.
result Enjoys a population-level safety guarantee and outperforms existing methods on real-world causal discovery tasks.

Bayesian metalearning improves performance in linear bandits with misspecified priors.

problem Improper priors lead to suboptimal performance in sequential decision-making.
method Proves performance bounds for metalearning priors in stochastic linear bandits and develops a metalearning algorithm.
result Metalearning can improve performance by learning the prior from multiple tasks.

The paper extends and applies a new shrinkage prior in Bayesian factor analysis.

problem Estimating the number of factors in sparse Bayesian factor analysis.
method Introduces and extends a generalized cumulative shrinkage process (CUSP) prior.
result Exchangeable spike-and-slab shrinkage priors imply increasing shrinkage as the column index increases.

Bayesian method corrects for model selection multiplicity in regression.

problem Model selection multiplicity in regression analysis.
method Developed a Bayesian prior distribution based on Holm procedure analogy.
result Adequate multiplicity correction requires sparsity not provided by recommended priors.

New method speeds up NIR spectroscopy calibration by 400x.

problem Efficient preprocessing selection in NIR spectroscopy.
method Operator-adaptive PLS and Ridge regression.
result Significant reduction in fitting time with comparable prediction quality.

Study characterizes training and test risks for MAP regression with Gaussian priors.

problem Understanding high-dimensional behavior of regularized linear regression with informative priors.
method Maximum a posteriori (MAP) regression with Gaussian priors, using random matrix theory.
result Closed-form risk formulas reveal the bias-variance-prior tradeoff and explain double descent.

This work tackles the challenge of Bayesian deep learning by proposing a new framework for matching Gaussian process priors with neural network parameters.

problem The challenge of specifying priors over neural network parameters, which affects the induced functional prior and is uncontrolled.
method The approach involves defining functional priors using Gaussian processes and matching these priors with the functional prior of neural networks through the minimization of Wasserstein distance.
result The proposed framework offers systematic performance improvements over alternative priors and approximate Bayesian deep learning approaches.

This paper uses reference priors to improve deep learning models with unlabeled and labeled data.

problem Improving deep learning models with limited labeled data and unlabeled data from the same or related tasks.
method Develops and applies generalizations of reference priors for deep networks to exploit unlabeled and labeled data.
result Demonstrates new semi-supervised learning and pretraining methods for transfer learning.

Proposes a new prior for complex models to improve prediction accuracy.

problem Difficulty in specifying priors for complex models like neural networks.
method Predictive complexity priors defined by comparing model predictions to a reference model, transferred to parameters via change of variables.
result Improves model predictions by reducing unintuitive effects of traditional priors.

We construct geometric shrinkage priors for Kählerian signal filters. Based on the characteristics of Kähler manifolds, an efficient and robust algorithm for finding superharmonic priors which outperform the Jeffreys prior is introduced. Several ansätze for the Bayesian predictive priors are also suggested. In particul…

2014-08-28abs ↗pdf ↗

Statsformer validates and adapts LLM-derived semantic priors for improved supervised learning.

problem Unreliable semantic priors from LLMs can degrade supervised learning performance.
method Adapts LLM-derived feature scores into a family of learner-specific prior-injection mechanisms, calibrating their influence using out-of-fold validation.
result Improves prediction performance by adaptively downweighting unreliable LLM priors, ensuring a guardrailed statistical learning system.

SAHMM-VAE separates sources adaptively using hidden Markov priors.

problem Unsupervised blind source separation.
method Source-wise adaptive Hidden Markov prior variational autoencoder.
result Different latent dimensions align with different source-specific temporal organizations.

BNNpriors library improves Bayesian neural network inference with various prior distributions.

problem Challenges in choosing good prior distributions for Bayesian neural networks.
method State-of-the-art Markov Chain Monte Carlo inference with a wide range of predefined priors.
result Facilitates foundational discoveries on the nature of the cold posterior effect.

GOAT improves attention mechanisms by learning better priors.

problem Standard attention mechanisms use a naive uniform prior, limiting flexibility and generalization.
method GOAT introduces a trainable, continuous prior that replaces the uniform assumption, maintaining compatibility with optimized kernels.
result GOAT avoids representational trade-offs and learns an extrapolatable prior that combines positional flexibility with length generalization.

We study the problem of learning shared structure \emph{across} a sequence of dynamic pricing experiments for related products. We consider a practical formulation where the unknown demand parameters for each product come from an unknown distribution (prior) that is shared across products. We then propose a meta dynami…

2019-02-28abs ↗pdf ↗

Weak diffusion priors can still perform well in inverse problems.

problem Using mismatched or low-fidelity diffusion priors in inverse problems.
method Extensive experiments and theoretical analysis combining Bayesian-consistency theory and local-correlation analysis.
result Weak priors succeed when measurements are highly informative, and they fail in other regimes.

Optimality of TS with noninformative priors proven for Pareto model.

problem Optimality of Thompson Sampling with noninformative priors for Pareto bandits.
method Proved optimality of TS with certain probability matching priors, showed suboptimality with others, and found effectiveness of truncation procedures.
result TS with certain probability matching priors achieves optimal regret bound for Pareto model.

New meta-reinforcement learning method improves performance in finite-horizon MDPs.

problem Improving meta-reinforcement learning in finite-horizon MDPs with shared optimal action-value functions.
method Proposes MTSRL and MTSRL+ algorithms with learned priors and covariance, coupled with prior-alignment technique for meta-regret guarantees.
result Achieves meta-regret guarantees with learned priors and covariance, outperforming prior-independent RL and bandit-only meta-baselines.