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

66132198264 · Jun 202019922001200920172026
48 results for differentiable attribution

Paper analyzes multi-attribute data to estimate differences in Gaussian graphical models.

problem Estimating differences in two Gaussian graphical models with similar structure.
method Group lasso penalized D-trace loss function and ADMM algorithm for optimization.
result Consistency in support recovery and estimation in high-dimensional settings established.

New credit attribution methods for machine learning models using relaxed stability guarantees.

problem Ensuring proper attribution in generative models trained on existing works.
method Proposed new definitions of stability that allow for non-stable processing of a subset of datapoints with permission.
result Extended well-studied stability notions and provided a comprehensive characterization of learnability.

Paper estimates differences in multi-attribute Gaussian graphical models using non-convex penalties.

problem Estimating differences in multi-attribute Gaussian graphical models with similar structure.
method Penalized D-trace loss function with non-convex (log-sum and SCAD) penalties, proximal gradient descent methods.
result Theoretical analysis and numerical examples support consistency in support recovery and estimation.

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.

Generic generation and manipulation of text is challenging and has limited success compared to recent deep generative modeling in visual domain. This paper aims at generating plausible natural language sentences, whose attributes are dynamically controlled by learning disentangled latent representations with designated…

2017-03-02abs ↗pdf ↗

Optimal LDP mechanisms reduce data unfairness in classification.

problem Reducing data unfairness in classification models.
method Developed a closed-form optimal mechanism for binary attributes and a tractable framework for multi-valued attributes.
result Optimal LDP mechanisms improve fairness in classification while maintaining accuracy close to non-private models.

Machine learning algorithms are increasingly involved in sensitive decision-making process with adversarial implications on individuals. This paper presents mdfa, an approach that identifies the characteristics of the victims of a classifier's discrimination. We measure discrimination as a violation of multi-differenti…

2019-03-18abs ↗pdf ↗

New method predicts model output distributions to improve data attribution.

problem Traditional training data attribution ignores randomness in model training.
method Distributional Training Data Attribution (d-TDA) using influence functions.
result Influence functions are effective and emerge naturally from d-TDA.

New method optimizes fairness in predictive models for continuous sensitive attributes.

problem Enforcing full statistical independence on continuous sensitive attributes is too restrictive.
method Functional bilevel optimization (FBO) and ITD algorithms.
result Achieves lowest or near-lowest fairness-accuracy regret on synthetic and real datasets.

AuxiLearn combines auxiliary tasks into a single loss function.

problem Improving neural network performance on a main task using auxiliary tasks.
method Implicit differentiation to learn a network that combines auxiliary tasks into a single coherent objective function.
result AuxiLearn consistently outperforms competing methods in various tasks and domains.

A new method, VIF, calculates influence for non-decomposable losses efficiently.

problem Efficiently calculating influence for complex machine learning models with non-decomposable losses.
method Revisiting influence function from robust statistics, proposing Versatile Influence Function (VIF) for any non-decomposable loss.
result VIF method is up to 10^3 times faster than brute-force methods and closely matches influence results.

ASTRA improves TDA by more accurately approximating iHVP.

problem Improving insights into training data attribution.
method ASTRA uses EKFAC-preconditioner on Neumann series iterations to accurately approximate iHVP.
result Improving iHVP approximation significantly improves TDA performance.

Feature attribution methods, or saliency maps, are one of the most popular approaches for explaining the decisions of complex machine learning models such as deep neural networks. In this study, we propose a stochastic optimization approach for the perturbation-based feature attribution method. While the original optim…

2018-07-12abs ↗pdf ↗

Differentiable Masking reveals how neural models make decisions across layers.

problem Intractable and expensive approximate search for input relevance in deep models.
method Differentiable Masking learns to mask inputs while maintaining differentiability.
result Reveals how decisions are formed across network layers in BERT models.

The paper classifies adjacencies in LL^\infty-Delaunay triangulations of abelian differentials.

problem Classifying adjacencies in LL^\infty-Delaunay triangulations of abelian differentials.
method Classification through a finite simplicial complex construction.
result A finite simplicial complex with the same homotopy type as H(κ)\mathcal H(κ) is constructed.

Motivated by settings in which predictive models may be required to be non-discriminatory with respect to certain attributes (such as race), but even collecting the sensitive attribute may be forbidden or restricted, we initiate the study of fair learning under the constraint of differential privacy. We design two lear…

2018-12-06abs ↗pdf ↗

A new method learns fair classifiers without sacrificing accuracy.

problem Designing fair classifiers that do not discriminate based on sensitive attributes.
method A model-agnostic multi-objective architecture using a differentiable relaxation of fairness notions.
result Our method achieves lower loss of accuracy compared to current debiasing algorithms.

A novel algorithm for unsupervised graph representation learning combining coarsening and mutual information maximization.

problem Current limitations in unsupervised graph representation learning, especially in embedding new graphs and considering both micro- and macro-structures.
method Combines coarsening with mutual information maximization to produce high-quality embeddings.
result The algorithm produces high-quality embeddings that are competitive with state-of-the-art methods.

Joint models are a common and important tool in the intersection of machine learning and the physical sciences, particularly in contexts where real-world measurements are scarce. Recent developments in rainfall-runoff modeling, one of the prime challenges in hydrology, show the value of a joint model with shared repres…

2019-11-21abs ↗pdf ↗

Optimal pre-processing reduces disparate impact by minimizing total variation distance.

problem Achieving fairness in data outputs based on protected attributes.
method Using pre-processing to enforce fairness, minimizing total variation distance between pre-processed and original data distributions.
result The problem of fairness can be formulated as a linear program, efficiently solvable.

Estimates drift functions in SDEs using denoising diffusion models.

problem Estimating time-homogeneous drift functions in multivariate SDEs.
method Formulates drift estimation as a denoising problem, trains a conditional diffusion model.
result Proposed estimator matches classical methods in low dimensions and remains competitive in higher dimensions.

Cosmos models scenes using neural encodings and symbolic attributes for compositional generalization.

problem Modeling scenes with high performance on unseen input scenes composed of known visual elements.
method Neurosymbolic grounding with neurosymbolic scene encodings and attention mechanisms.
result Establishes a new state-of-the-art for compositional generalization in world modeling.

Proposes a Taylor framework to unify and analyze attribution methods.

problem Lack of a unified guideline for feature contribution assignment in machine learning models.
method Introduces a Taylor attribution framework to model the attribution problem and reformulates fourteen mainstream methods.
result Empirically validates the Taylor reformulations and reveals a positive correlation between performance and principles followed.

Unified framework for analyzing machine learning model attributions.

problem Lack of a general and theoretical framework for understanding attribution methods.
method Proposes a Taylor attribution framework to unify and analyze seven mainstream attribution methods.
result Established three principles for good attribution and empirically validated the Taylor reformulations.

TREX explains tree ensembles by identifying key training examples.

problem Identifying which training examples most influence tree ensemble predictions.
method TREX builds a surrogate model using a kernel that captures tree ensemble structure, approximating the original model.
result TREX provides accurate and effective explanations for tree ensembles.

Facial attribute editing aims to manipulate single or multiple attributes of a face image, i.e., to generate a new face with desired attributes while preserving other details. Recently, generative adversarial net (GAN) and encoder-decoder architecture are usually incorporated to handle this task with promising results.…

2017-11-29abs ↗pdf ↗

Wavelet Attribution Method (WAM) improves feature attribution for deep models.

problem Inability of pixel-based heatmaps to capture data structure and variability in feature attribution.
method Wavelet domain for feature attribution, leveraging spatial and scale-localized properties of wavelet coefficients.
result WAM provides quantitatively superior explanations across audio, image, and volume modalities.

Proposes VCLANC for attributed network clustering using node and attribute embeddings.

problem Lack of mutual affinity exploitation between nodes and attributes in graph convolution.
method Dual variational auto-encoders for node and attribute embeddings, Gaussian mixture model priors, mutual distance and clustering assignment hardening losses.
result Demonstrates effectiveness on real-world attributed network datasets.

BUDS balances privacy and utility by shuffling data, achieving strong privacy with minimal loss.

problem Balancing privacy and utility in crowd-sourced statistical databases.
method One-hot encoding, iterative shuffling, loss estimation, risk minimization.
result Achieves ε=0.02ε= 0.02 for privacy, maintaining a privacy bound of ε=ln[t/((n11)S)]ε= ln [t/((n_1 - 1)^S)].

Lecture notes introduce Abelian differentials and their flat surfaces, focusing on families and Teichmüller dynamics.

problem Study of Abelian differentials and their geometric properties.
method Associate flat surfaces to Abelian differentials and analyze their families under GL2+(R)GL_2^{+}(\mathbb{R}) action.
result Properties of orbit of Abelian differentials under Teichmüller dynamics.