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

25.0%50.0%75.0%100.0% · Sep 199219922001200920172026
48 results for differentiable data selection

New algorithm maintains privacy while improving model performance in selective release.

problem Privacy degradation and slow convergence in DPSGD.
method Differentially Private Selective Release based on Clipped Gradients (DPSR-CG).
result Maintains strict privacy guarantees while achieving exceptional model performance.

Novel privatization framework for high-dimensional variable selection with differential privacy.

problem High-dimensional controlled variable selection with rigorous FDR control under differential privacy constraints.
method Gaussian Johnson-Lindenstrauss Transformation for privatizing the knockoff matrix.
result The proposed private variable selection procedure maintains statistical power even under strict privacy budgets.

A DP method selects best sparse models in high dimensions efficiently.

problem Model selection in high-dimensional sparse linear regression under privacy constraints.
method Differential privacy (DP) with exponential mechanism and Metropolis-Hastings algorithm.
result The method identifies active features quickly under privacy constraints.

Differentially Private algorithms often need to select the best amongst many candidate options. Classical works on this selection problem require that the candidates' goodness, measured as a real-valued score function, does not change by much when one person's data changes. In many applications such as hyperparameter o…

2018-11-19abs ↗pdf ↗

New method finds minimum in noisy data, useful for model selection.

problem Finding the index of the minimum value in noisy observations.
method Developed an asymptotically normal test statistic integrating cross-validation and differential privacy.
result Achieves a favorable bias-variance trade-off in practical scenarios.

A novel method for feature selection using a reparameterized logitNormal distribution.

problem Feature selection for reconstruction in high-dimensional data.
method Introducing a reparameterization of the logitNormal distribution to address differentiability and covariance issues.
result The method provides an effective exploration scheme and efficient feature selection for reconstruction.

FedSel uses local differential privacy to protect data privacy in federated SGD.

problem Privacy leakage from gradients in federated SGD.
method Two-stage framework with top-k dimension selection and gradient accumulation.
result FedSel reduces privacy leakage by privately selecting important dimensions.

AMES framework selects optimal embedding space for latent graph inference.

problem No principled method for choosing the best embedding space for latent graph inference.
method Differentiable AMES framework using backpropagation to select optimal embedding space.
result Consistently achieves comparable or superior results across multiple datasets.

In this paper, we propose a new framework for designing fast parallel algorithms for fundamental statistical subset selection tasks that include feature selection and experimental design. Such tasks are known to be weakly submodular and are amenable to optimization via the standard greedy algorithm. Despite its desirab…

2019-03-06abs ↗pdf ↗

Selective forgetting method cleans deep network weights of forgotten data.

problem Selective forgetting of specific data subsets in deep neural networks.
method A method to scrub weights clean of forgotten data without retraining.
result The method ensures indistinguishability of probing functions from a non-forgotten network.

Improved algorithm for selecting a hypothesis locally privately with fewer queries.

problem Locally private hypothesis selection with minimal privacy-preserving queries.
method Introduces a Scheffé graph to reduce query complexity for hypothesis selection.
result Algorithm performs O~(k3/2)\tilde{O}(k^{3/2}) queries, improving on previous methods.

New algorithm selects best distribution privately in nearly-linear time.

problem Estimating the best distribution from samples under differential privacy constraints.
method Differentially private algorithm with nearly-linear time complexity and optimal approximation factor.
result Achieves optimal approximation factor of 3 with modest sample complexity increase.

This work improves SINDy-type algorithms for system identification using score-guided dictionary selection.

problem Improving accuracy and interpretability in dynamical system identification.
method Score-guided library selection to refine dictionary terms in sparse regression.
result Score-guided methods enhance SINDy's robustness in discovering governing equations.

New methods detect continuous variation in single-cell data.

problem Continuous variation within and between cell types not detected by discrete analyses.
method Three topologically motivated mathematical methods for unsupervised feature selection.
result Detect additional biologically meaningful genes with coherent expression patterns.

EPD method accurately captures parameter distributions from RCS data.

problem Limitations of traditional methods in estimating parameter distributions from RCS data.
method EPD method generates synthetic trajectories, estimates parameters, and selects parameters based on discrepancy.
result EPD provides accurate distribution of parameters without data loss.

Study solves optimal portfolio selection using HJB equation.

problem Optimal portfolio selection problem.
method Maximal monotone operator method, Banach fixed-point theorem, Fourier transform, monotone operators technique.
result Existence and uniqueness of solution to HJB equation.

Paper discovers governing equations from data using differential invariants.

problem Discovering partial differential equations from data is challenging.
method The paper proposes a pipeline based on differential invariants to reduce the search space and adhere to symmetry.
result DI-SINDy method outperforms other symmetry-informed methods in PDE discovery.

The paper addresses hypothesis selection with local differential privacy, requiring more samples than non-private methods.

problem Hypothesis selection under local differential privacy constraints.
method Develops algorithms for hypothesis selection with local differential privacy, achieving near-optimal sample and round complexities.
result Non-interactive algorithms for kk-wise simple hypothesis testing require O~(k)\tilde O(k) samples and O(loglogk)O(\log \log k) rounds of interaction.

The study extends GBM to include stable nonzero prices and finds a pronounced potential well.

problem The standard GBM model cannot describe stable nonzero prices in financial dynamics.
method Generalized GBM with polynomial drift of order q, model selection, and Markov chain Monte Carlo ensembles of potential functions.
result The optimal model for financial data is q=2, indicating the existence of a stable price.

DDS uses a scorer to adaptively weigh data during training, improving model performance.

problem Efficiently optimizing data usage during machine learning training.
method Differentiable Data Selection (DDS) using a learnable scorer network and a reward signal.
result DDS delivers strong and consistent improvements over baselines on machine translation and image classification tasks.

This work refines grid size selection for non-interactive private KK-means clustering.

problem Choosing the optimal number of grids for privatized KK-means clustering.
method Proposes a refined grid-size selection rule to minimize expected deviation in the K-means objective function.
result The proposed strategy results in more accurate clustering compared to prior work, even under tight privacy budgets.

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.

New optimizer improves privacy-protected hyperparameter tuning.

problem No practical methods for differentially private hyperparameter selection.
method Study honest hyperparameter selection under DP, show adaptive optimizers like DPAdam have an advantage.
result DPAdam optimizes hyperparameters more efficiently under DP constraints.

Cluster-DP improves differential privacy in randomized experiments by clustering data.

problem Reducing variance in causal effect estimation from differentially private data.
method Cluster-DP leverages a given cluster structure to improve the privacy-variance trade-off.
result Selecting higher-quality clusters decreases the variance penalty without compromising privacy guarantees.

LDP-Fed protects privacy in federated learning with neural networks.

problem Privacy protection for high-dimensional, continuous model parameters in federated learning.
method Local Differential Privacy (LDP) for repeated collection of model training parameters, selection and filtering of parameter updates.
result LDP-Fed achieves model accuracy comparable to non-private methods while preserving privacy.

In this paper, we present a differential privacy version of convex and nonconvex sparse classification approach. Based on alternating direction method of multiplier (ADMM) algorithm, we transform the solving of sparse problem into the multistep iteration process. Then we add exponential noise to stable steps to achieve…

2019-08-02abs ↗pdf ↗