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.

168,742 papers · 148 categories

Trend · papers per month

62123185246 · May 202619922001200920172026
48 results for target recovery

We reveal a model rank that predicts successful recovery of target functions at overparameterization.

problem Understanding the mysterious good generalization performance of overparameterized nonlinear models.
method Rank stratification and linear stability theory for general nonlinear models.
result Linearly stable functions are preferred by nonlinear training, and model rank predicts minimal training data size.

Symmetry helps VI recover certain statistics.

problem Understanding how symmetry in variational inference affects the recovery of statistics.
method Developed a general theory of symmetry-induced statistic recovery in variational inference.
result Symmetry can force the recovery of certain statistics in VI, even under model misspecification.

New framework uses score-based priors to solve ill-conditioned polynomial equations, improving signal recovery from noisy data.

problem Recovering signals from low-order moments in inverse problems, especially ill-conditioned polynomial equations.
method Integrates score-based diffusion priors with moment-based estimators to regularize and solve nonlinear inverse problems.
result Diffusion priors improve recovery from third-order moments and make super-resolution MTD feasible.

Study shows DNNs can recover functions with fewer samples than model parameters at overparameterization.

problem Determining reliable function recovery in overparameterized deep neural networks.
method Introducing 'local linear recovery' (LLR) and proving upper bounds on sample sizes for recovery.
result Upper bounds on optimistic sample sizes for function recovery in overparameterized DNNs are achieved.

Transfer learning improves loan recovery rate forecasting under data scarcity.

problem Data scarcity in loan portfolios limits RR modeling accuracy.
method Introduces FT-MDN-Transformer, a mixture-density tabular Transformer architecture for TL.
result FT-MDN-Transformer outperforms baseline models in RR forecasting, especially under covariate and conditional shifts.

Recovery of low-rank matrices has recently seen significant activity in many areas of science and engineering, motivated by recent theoretical results for exact reconstruction guarantees and interesting practical applications. A number of methods have been developed for this recovery problem. However, a principled meth…

2011-02-25abs ↗pdf ↗

A hierarchical model shows how scaling laws emerge from sequential feature recovery.

problem Emergence of scaling laws from feature learning in multi-layer networks.
method Layer-wise spectral algorithm adapted to compositional structure, sequential feature detection.
result Sequential detection of latent features, leading to explicit power-law decay of prediction error.

Method separates target signal properties from noisy mixtures.

problem Signal recovery from noisy mixtures with specific statistical properties.
method Statistical component separation method using noise samples and matching statistics.
result Method outperforms standard denoising methods in recovering target signal properties.

Telecommunication (Telco) outdoor position recovery aims to localize outdoor mobile devices by leveraging measurement report (MR) data. Unfortunately, Telco position recovery requires sufficient amount of MR samples across different areas and suffers from high data collection cost. For an area with scarce MR samples, i…

2019-12-10abs ↗pdf ↗

Integrating wind power into the grid is challenging because of its random nature. Integration is facilitated with accurate short-term forecasts of wind power. The paper presents a spatio-temporal wind speed forecasting algorithm that incorporates the time series data of a target station and data of surrounding stations…

2015-03-04abs ↗pdf ↗

Localizing targets of interest in a given hyperspectral (HS) image has applications ranging from remote sensing to surveillance. This task of target detection leverages the fact that each material/object possesses its own characteristic spectral response, depending upon its composition. As signatures\textit{signatures} of diff…

2019-02-26abs ↗pdf ↗

Convex optimization method recovers low-rank matrices from rank-one projections efficiently.

problem Recovering low-rank matrices from limited rank-one projections.
method Unlifted convex optimization with subgradient method.
result The estimator succeeds with high probability if the number of measurements exceeds r2(d1+d2)r^2 (d_1+d_2) up to logarithmic factors.

We connect Causal inference and low-rank recovery via RDT and free probability theory.

problem Determining the applicability of causal inference via low-rank recovery.
method Random Duality Theory, free probability theory, and mathematical rigor.
result Exact closed-form worst case phase transitions for causal inference.

Optimal joint separation condition for radar and communications channels in dual-blind deconvolution.

problem Recovering information from overlaid radar and communications signals with unknown channels.
method Extremal functions from Beurling-Selberg interpolation theory for joint separation, nuclear norm minimization for matrix retrieval, and MUSIC for parameter estimation.
result Guaranteed well-conditioned Vandermonde matrix for MUSIC, validating theoretical findings.

Machine learning improves sub-hourly precipitation data recovery.

problem Missing precipitation data at sub-hourly intervals.
method Two-step process: rain/non-rain classification and rain intensity prediction.
result Machine learning outperforms traditional methods in predicting missing precipitation data.

Method identifies unknown intervention targets in structural causal models from diverse data.

problem Identifying unknown intervention targets in structural causal models from heterogeneous data.
method Two-phase approach: first recovers exogenous noises, second matches with endogenous variables.
result Proposed method uniquely identifies intervention targets under causal sufficiency assumption.

U-aggregation combines multiple models without labels for better risk prediction.

problem Challenges in selecting best model for new populations due to limited data and lack of true labels.
method U-aggregation, an unsupervised model aggregation method that integrates pre-trained models without observed labels.
result U-aggregation improves genetic risk prediction of complex traits using publicly available models.

Paper proposes scalable algorithm to estimate intervention targets in linear models.

problem Estimating intervention targets in linear models from observational and interventional data.
method The paper proposes a scalable algorithm that estimates intervention sites from the difference between precision matrices of observational and interventional datasets.
result The algorithm consistently identifies all intervention targets and updates observational Markov equivalence classes to interventional ones.

Unified framework for distribution shift estimation, explanation, and improvement.

problem Estimating, explaining, and improving model performance on target domains with distribution shift.
method Entropic Projection Alignment (EPA) aligns source and target distributions by matching moments and minimizing KL divergence.
result EPA consistently outperforms state-of-the-art baselines while offering computational efficiency.

Study uncovers new phase transitions in asymmetric causal inference scenarios.

problem Understanding typical phase transitions in asymmetric causal inference.
method Combining Causal inference (C-inf) and Low-rank recovery (LRR) with Random duality - Free probability theory (RDT-FPT).
result Discovering a doubling low-rankness phenomenon in asymmetric scenarios.

Scaled gradient descent improves matrix recovery for ill-conditioned matrices with optimal sampling complexity.

problem Recovering low-rank matrices from limited measurements efficiently and accurately.
method Scaled gradient descent (ScaledGD) with optimal sample complexity and improved iteration complexity.
result ScaledGD achieves optimal sample complexity and improved iteration complexity for ill-conditioned matrices.

This paper explores the information-theoretic limitations of graph property testing in zero-field Ising models. Instead of learning the entire graph structure, sometimes testing a basic graph property such as connectivity, cycle presence or maximum clique size is a more relevant and attainable objective. Since property…

2017-09-20abs ↗pdf ↗

A model learns causal representations from high-dimensional data.

problem Challenges in learning causal representations from high-dimensional data.
method Formulated a latent variable decoder model, Decoder BCD, for Bayesian causal discovery.
result Shows that using known intervention targets as labels helps in unsupervised Bayesian inference over structure and parameters.

The paper examines how gradient descent stabilizes low-rank matrix factorization in noisy conditions.

problem Stability of low-rank implicit regularization in perturbed deep matrix factorization.
method Derives spectral conditions for gradient descent to exhibit a low-rank phase in noiseless settings and analyzes perturbed dynamics.
result Gradient descent converges to a low-rank solution under perturbation, with explicit dependence on perturbation size.

New method fuses audio and magnetic data to identify underlying subspaces.

problem Identifying complex trends in multi-modality data.
method Robust Group Subspace Recovery (RoGSuRe) algorithm based on group sparsity and bi-sparsity pursuit.
result Competitive performance in clustering and classification of multi-modal data.

We derive an arbitrage free relationship between recovery swap rates, digital default swap spreads and conventional CDS spreads, and argue that the fair forward recovery rate used in recovery swaps must contain a convexity premium over the expected recovery value.

2010-01-05abs ↗pdf ↗

Paper analyzes VI for location-scale families, proving robustness guarantees for mean and correlation recovery.

problem Misspecification in VI for intractable target densities.
method Variational inference on location-scale families with symmetries.
result VI recovers mean and correlation matrix under specific symmetries.

HTFM improves mode coverage and tail-statistic recovery for heavy-tailed data.

problem Tackles heavy-tailed data in various domains with rare events.
method Proposes a framework using clock-conditioned Gaussian sources and truncated logsignature features.
result Improves mode coverage, sample quality, and tail-statistic recovery over Gaussian flow matching and baselines.

Method uses Seq2Seq learning to automatically generate recovery commands for ICT systems.

problem Manual decision-making for recovery commands is time-consuming and error-prone.
method Seq2Seq neural network model trained on past logs and commands.
result The model can estimate accurate recovery commands from new failures.