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.

169,341 papers · 148 categories

Trend · papers per month

195390585780 · Jun 202019922001200920182026
48 results for Inference tasks

OCEAN infers online task identities from context variables.

problem Online task inference for compositional tasks with context adaptation.
method Variational inference framework OCEAN models global and local context variables in a joint latent space.
result OCEAN provides more effective task inference with sequential context adaptation.

Transformers infer tasks from context via two modes, geometrically shaped task vectors explain their behavior.

problem Understanding how transformers infer tasks from context and the geometric properties of task vectors.
method Synthetic setting to train small transformers, mathematical characterization of task-vector geometry and inference modes.
result Task-vector geometry shapes in-distribution and out-of-distribution behavior of transformers.

PPI uses proxy data to improve inference from limited labels across related tasks.

problem Statistical inference with limited labels across multiple related tasks.
method Prediction-powered inference framework that uses cross-task recalibration to improve power and accuracy.
result Cross-task recalibration can substantially reduce confidence interval widths when labels are scarce.

Selective inference improves multi-task neuroimaging analysis.

problem Improving predictive performance and modeling accuracy in neuroimaging studies.
method Proposes a framework for selective inference to jointly identify relevant covariates and conduct valid inference in a sparsity-inducing model.
result Selective inference yields tighter confidence intervals and more accurate signal recovery than single-task methods.

Aux-NAS uses auxiliary labels to improve primary task performance without extra inference cost.

problem Improving primary task performance using auxiliary labels without increasing inference cost.
method Architecture-based approach with a flexible asymmetric structure for primary and auxiliary tasks, using Neural Architecture Search (NAS) to evolve networks with only primary-to-auxiliary connections.
result Achieves improved performance on multiple tasks without increasing inference cost.

New method improves crowdsourcing efficiency and inference of problem properties.

problem Crowdsourcing allocation strategies introduce bias, affecting inference of task difficulty and worker properties.
method Decision-Explicit Probability Sampling (DEPS) to infer problem properties accurately.
result DEPS outperforms baseline methods in inferring problem properties while maintaining efficiency gains.

Paper proposes learnable topological features for efficient phylogenetic inference.

problem Finding appropriate topological structures for phylogenetic inference tasks requires significant design effort and domain expertise.
method Combines raw node features with graph neural networks to automatically adapt to different tasks.
result Demonstrates effectiveness and efficiency on simulated and real data phylogenetic inference tasks.

Paper extends multi-task Gaussian Cox processes for heterogeneous tasks.

problem Modeling multiple heterogeneous correlated tasks jointly.
method Data augmentation and mean-field approximation for non-conjugate Bayesian inference.
result Demonstrates improved performance and inference on synthetic and real data.

Bayesian TAML balances meta-knowledge and task-specific learning for imbalanced tasks.

problem Meta-learning approaches struggle with varying instance and class numbers and distributional differences.
method Bayesian inference framework with variational inference to adaptively balance meta-knowledge and task-specific learning.
result Bayesian TAML significantly outperforms existing meta-learning approaches on imbalanced datasets.

Unified framework for simulation-based inference learns a single model for multiple tasks.

problem Simulation-based inference for multiple tasks with limited model retraining.
method Unified flow-matching generative model with query-aware masking distribution.
result Competitive performance on various inference tasks and real-world problems.

MTNPs jointly model multiple correlated tasks from various sources.

problem Naive NPs can only model a single stochastic process and infer tasks independently.
method MTNPs are a hierarchical extension of NPs that jointly infer tasks from multiple stochastic processes, considering inter-task correlation and handling incomplete data.
result MTNPs successfully model multiple tasks jointly, discovering and exploiting their correlations in various real-world data.

New model optimizes worker-task specialization for crowdsourcing.

problem Inferring correct labels from noisy answers across varying worker and task skills.
method Introduced a dd-type specialization model to account for varying worker and task types, and proposed algorithms achieving optimal sample complexity.
result Optimal label inference algorithms for crowdsourcing with unknown worker and task types.

Paper tackles high-order inference in structured prediction tasks.

problem Maximizing a score function on the space of labels in high-order Markov random fields.
method Generative model approach with two-stage convex optimization algorithm.
result Success in general high-order inference problems driven by hyperedge expansion properties.

Noise injection improves inference privacy in DNN models.

problem Malicious servers can infer sensitive attributes from input data.
method Adaptive Noise Injection (ANI) using a lightweight DNN on the client.
result Significant improvement in privacy (up to 48.5% degradation in sensitive-task accuracy with <1% degradation in primary accuracy).

This paper reviews causal inference methods for time series data.

problem Estimating treatment effects and identifying causal relations from time series data.
method Comprehensive review of approaches for treatment effect estimation and causal discovery.
result Provides a list of evaluation metrics and datasets for time series causal inference.

HuMaINs combines human and machine strengths for better inference tasks.

problem Improving inference performance through human-machine collaboration.
method Novel signal processing and machine learning solutions for HuMaINs architecture.
result HuMaINs achieves higher performance than either humans or machines individually.

Data science redefines causal inference from observational data, classifying tasks into description, prediction, and counterfactual prediction.

problem Widespread misunderstandings about data science's role in causal inference from observational data.
method Organizing data science tasks into three classes: Description, prediction, and counterfactual prediction (including causal inference).
result The necessity of subject-matter expert knowledge for causal analyses in data science.

Novel meta-RL strategy improves efficiency in learning novel tasks.

problem Efficiency in learning novel tasks using deep RL.
method Decomposes meta-RL into task-exploration, task-inference, and task-fulfillment; uses deep networks and a task encoder.
result Improves sample efficiency and mitigates meta-overfitting.

Active inference implemented for high-dimensional tasks shows efficient exploration and improved sample efficiency.

problem Achieving efficient exploration and learning in complex, uncertain environments.
method Active inference framework applied to high-dimensional tasks, with Bayesian evidence maximization.
result Order of magnitude increase in sample efficiency over model-free baselines.

Meta-learn Bayesian inference for task-specific BNNs using amortised inference.

problem Efficiently learning Bayesian inference for small-scale probabilistic meta-learning.
method Replace global inducing points with actual data to create a set of approximate likelihoods, train a meta-model to learn these parameters across related datasets.
result Meta-learned inference can be applied to task-specific BNNs, improving efficiency and scalability.

Paper proposes a method for learning and inferring movement using deep generative models.

problem Challenges in learning and inferring movement due to high dimensionality and varied environments.
method Formulates motion planning as learning on a directed graphic model and uses deep generative models.
result Flexibly incorporates task descriptors and context information for long-term planning.

SOFARI improves inference on multi-task learning latent factors.

problem Challenges in precise inference on multi-task learning latent factor matrices.
method High-dimensional manifold-based Neyman near-orthogonality inference on Stiefel manifold structure.
result Easy-to-use bias-corrected estimators for latent factor vectors and singular values with asymptotic normal distributions.

SDM Policy accelerates inference for robotic tasks while maintaining high action quality.

problem Prolonged inference times in diffusion-based policies for high-frequency control tasks.
method Two-stage optimization: score matching and distribution matching; dual-teacher mechanism.
result 6x inference speedup with state-of-the-art action quality.

Proposes a Bayesian federated learning method for diverse tasks.

problem Current federated learning approaches focus on homogeneous tasks, ignoring task diversity.
method Integrates multi-task learning with MOGP at the local level and federated learning at the global level.
result Demonstrates superior predictive performance and uncertainty calibration on diverse tasks.

Neurally-Guided Structure Inference combines search and data-driven methods for efficient, robust structure inference.

problem Combining the advantages of exhaustive search and data-driven methods for structure inference.
method Neurally-Guided Structure Inference (NG-SI) uses a neural network to guide hierarchical search over structures.
result NG-SI outperforms search-based and data-driven methods on probabilistic matrix decomposition and symbolic program parsing.

We solve varying-coefficient models with Gaussian process priors efficiently.

problem Learning varying relationships between input and output with additional task variables.
method Isotropic Gaussian process priors for varying-coefficient models, leading to efficient inference.
result Efficient inference for varying-coefficient models with Gaussian process priors.

Continuous-time flows unify inference and density estimation.

problem Efficient inference and robust density estimation for latent-variable models.
method Continuous-time flows (CTFs) as a diffusion-based framework for both tasks.
result CTFs achieve both inference and density estimation in a unified framework with theoretical guarantees.

Meta-RL algorithm improves sample efficiency and adaptability.

problem Challenges in meta-reinforcement learning, especially on-policy experience and task uncertainty.
method Develops an off-policy meta-RL algorithm that probabilistically infers task variables.
result Significantly outperforms prior algorithms in sample efficiency and asymptotic performance.

CInA method uses attention to improve causal inference.

problem Challenges in causal inference, especially in complex tasks.
method CInA method utilizes self-supervised causal learning with multiple unlabeled datasets and transformer-type architecture.
result CInA effectively generalizes to out-of-distribution datasets and various real-world datasets.

Develops a scalable multi-task Gaussian process with neural embedding for improved performance.

problem High model complexity and limited model capability in multi-task Gaussian processes.
method Neural embedding of coregionalization, advanced variational inference, sparse approximation.
result Higher prediction quality and better generalization of the NSVLMC model.