FRInGe: Distribution-Space Integrated Gradients with Fisher--Rao Geometry

• URL: http://arxiv.org/abs/2605.06404v1
• Date: Thu, 07 May 2026 15:12:15 GMT
• Title: FRInGe: Distribution-Space Integrated Gradients with Fisher--Rao Geometry
• Abstract summary: We propose Fisher--Rao Integrated Gradients (FRInGe), which defines both the reference and schedule in predictive distribution space.<n> FRInGe replaces input baselines with a maximum-entropy predictive reference and follows a Fisher-Rao geodesic on the probability simplex.
• Score: 4.823870413661438
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Gradient-based attribution methods are model-faithful and scalable, but Integrated Gradients (IG) can be brittle because explanations depend on heuristic baselines, straight-line paths, discretization, and saturation. We propose Fisher--Rao Integrated Gradients (FRInGe), which defines both the reference and interpolation schedule in predictive distribution space. FRInGe replaces input baselines with a maximum-entropy predictive reference and follows a Fisher-Rao geodesic on the probability simplex. The corresponding input-space trajectory is realized through the pullback Fisher metric and stabilized by KL and Euclidean trust regions; attributions are obtained by integrating input gradients along this trajectory. Across six ImageNet architectures, FRInGe most clearly improves calibration-oriented attribution metrics, especially MAS scores, while remaining competitive on perturbation AUC and infidelity.

Related papers

• Fisher8: Stabilizing Neural Heteroscedastic Regression via Output-Layer Fisher Geometry [1.9336815376402718]
  Training neural networks to jointly predict mean and uncertainty estimates can be unstable.<n>We derive Fisher8, an output-layer gradient correction that reorients and rescales updates using Fisher geometry rather than Euclidean geometry.<n>Across multidimensional regression and representation-learning tasks, Fisher8 obtains superior likelihood--error tradeoffs, predicts calibrated uncertainty estimates, and learns rich uncertainty-aware feature spaces.
  arXiv  Detail & Related papers  (2026-08-11T02:10:51Z)
• LC-GRPO: Bridging Train-Inference Gap for Flow-Based GRPO with Langevin Correction [59.32834240526981]
  Flow-based generative models are typically sampled by solving a deterministic ordinary differential equation (ODE)<n>Existing GRPO methods for flow models replace the Euler-time ODE with aotropic differential equation (SDE) during training.<n>We introduce LC-GRPO, a flow-based GRPO framework with Langevin correction targeting the marginal distribution at the resulting timestep.
  arXiv  Detail & Related papers  (2026-08-06T04:47:57Z)
• Information-Geometric Forward Policy Training in GFlowNets [1.9480051045857554]
  We formulate forward-policy training in GFlowNets through the information geometry of the induced trajectory sampler.<n>Treating the forward policy as an induced trajectory sampler, we show that its intrinsic first-order geometry is given by the Fisher-Rao metric of the trajectory family.<n>We derive an exact decomposition of the trajectory Fisher into per-step conditional second moments.
  arXiv  Detail & Related papers  (2026-08-04T17:34:14Z)
• Widest-Path Reachability Fields for Connectivity-Preserving Slender Structure Segmentation [3.8331203995580565]
  We propose Widest-Path Reachability Fields (WPRF), a differentiable Max-Min reachability objective that redirects gradient flow to connectivity bottlenecks.<n>WPRF implements a differentiable Max-Min objective via dynamic programming on a domain-restricted graph.<n> Experiments across nine architectures and six datasets validate the bottleneck-focused gradient routing mechanism.
  arXiv  Detail & Related papers  (2026-07-08T08:04:06Z)
• Real-Time LiDAR Gaussian Splatting SLAM [2.0524609401792397]
  We present a real-time LiDAR-based framework for Splatting SLAM that tightly couples fast G-ICP registration with sphericalization-based dense mapping for large-scale sequences.<n>We reuse tracking-estimated local covariances to initialize Gaussians with range-aware scales and to derive surface normals for map optimization.<n>On the Newer College dataset, our method achieves an F-score of 86.78% using purely online trajectories at real-time speed.
  arXiv  Detail & Related papers  (2026-07-05T05:55:32Z)
• Global Convergence of Gradient Descent for Score Matching in Gaussian Mixtures via Reverse Fisher Divergence [67.12978375116599]
  We study an alternative objective: the reverse Fisher divergence, where the expectation is taken with respect to the student distribution.<n>We prove global convergence guarantees under a $widetilde(1)$-separation assumption on the target means.<n>Our rely on a new Lyapunov-based analysis of the gradient descent dynamics, showing that the reverse Fisher divergence has a much more favorable optimization landscape than the forward Fisher divergence.
  arXiv  Detail & Related papers  (2026-06-18T07:34:33Z)
• Clipping Bottleneck: Stabilizing RLVR via Stochastic Recovery of Near-Boundary Signals [83.0127582612634]
  Near-boundary Rescue (NSR) is a minimal, plug-and-play modification that retains out-of-bound tokens to recover lost signals.<n>NSR substantially improves training stability and delivers consistent gains over strong baselines such as DAPO and GSPO.
  arXiv  Detail & Related papers  (2026-05-21T16:45:31Z)
• Improved techniques for fine-tuning flow models via adjoint matching: a deterministic control pipeline [7.967038299436285]
  We propose a deterministic adjoint matching framework that formulates human preference alignment for flow-based generative models.<n>Building on this perspective, we introduce a truncated adjoint scheme that focuses on the terminal portion of the trajectory.<n>We further generalize the framework beyond standard KL-based regularization, allowing more flexible trade-offs between alignment strength and distributional preservation.
  arXiv  Detail & Related papers  (2026-05-07T17:12:47Z)
• Curvature-Aware PCA with Geodesic Tangent Space Aggregation for Semi-Supervised Learning [52.452902154360565]
  GTSA-PCA is a geometric extension of Principal Component Analysis.<n>It integrates curvature awareness and geodesic consistency within a unified spectral framework.<n>Our results position GTSA-PCA as a principled bridge between statistical and geometric approaches to dimensionality reduction.
  arXiv  Detail & Related papers  (2026-04-20T20:36:36Z)
• DOC-GS: Dual-Domain Observation and Calibration for Reliable Sparse-View Gaussian Splatting [80.43237927269575]
  In this paper, we revisit sparse-view 3DGS reconstruction from a new perspective.<n>We identify the core challenge as the unobservability of Gaussian primitive reliability.<n>Motivated by this observation, we propose a unified Dual-domain Observation and geometrics in rendered images framework.
  arXiv  Detail & Related papers  (2026-04-08T07:01:24Z)
• Bayesian Learning-Enhanced Navigation with Deep Smoothing for Inertial-Aided Navigation [8.510813384980262]
  BLENDS is a data-driven post-processing framework that augments the classical two-filter smoother with a transformer-based neural network.<n> BLENDS achieves horizontal position improvements of up to 63% over the baseline forward EKF.
  arXiv  Detail & Related papers  (2026-03-26T12:11:59Z)
• Generalizing GNNs with Tokenized Mixture of Experts [75.8310720413187]
  We show that improving stability requires reducing reliance on shift-sensitive features, leaving an irreducible worst-case generalization floor.<n>We propose STEM-GNN, a pretrain-then-finetune framework with a mixture-of-experts encoder for diverse computation paths.<n>Across nine node, link, and graph benchmarks, STEM-GNN achieves a stronger three-way balance, improving robustness to degree/homophily shifts and to feature/edge corruptions while remaining competitive on clean graphs.
  arXiv  Detail & Related papers  (2026-02-09T22:48:30Z)
• Variational Bayesian Flow Network for Graph Generation [54.94088904387278]
  We propose Variational Bayesian Flow Network (VBFN) for graph generation.<n>VBFN performs variational lifting to a tractable joint Gaussian variational belief family governed by structured precisions.<n>On synthetic and molecular graph datasets, VBFN improves fidelity and diversity, and surpasses baseline methods.
  arXiv  Detail & Related papers  (2026-01-30T03:59:38Z)
• Generative Stochastic Optimal Transport: Guided Harmonic Path-Integral Diffusion [0.0]
  We introduce Guided Harmonic Path-Integral Diffusion (GH-PID), a linearly-solvable framework for guided Optimal Transport.<n>A low-dimensional guidance protocol shapes the trajectory ensemble while preserving analytic structure.<n>GH-PID generates geometry-aware, trust-aware trajectories that satisfy the prescribed terminal distribution.
  arXiv  Detail & Related papers  (2025-12-05T05:18:15Z)
• Geometric Calibration and Neutral Zones for Uncertainty-Aware Multi-Class Classification [0.0]
  This work bridges information geometry and statistical learning, offering formal guarantees for uncertainty-aware classification in applications requiring rigorous validation.<n> Empirical validation on Adeno-Associated Virus classification demonstrates that the two-stage framework captures 72.5% of errors while deferring 34.5% of samples, reducing automated decision error rates from 16.8% to 6.9%.
  arXiv  Detail & Related papers  (2025-11-26T01:29:49Z)
• Convergence Properties of Natural Gradient Descent for Minimizing KL Divergence [0.0]
  We study the problem of minimizing the Kullback-Leibler (KL) divergence.<n>We analyze the behavior of gradient-based optimization algorithms under two dual coordinate systems.
  arXiv  Detail & Related papers  (2025-04-27T14:39:33Z)
• Last-Iterate Convergence of Adaptive Riemannian Gradient Descent for Equilibrium Computation [52.73824786627612]
  This paper establishes new convergence results for textitgeodesic strongly monotone games.<n>Our key result shows that RGD attains last-iterate linear convergence in a textitgeometry-agnostic fashion.<n>Overall, this paper presents the first geometry-agnostic last-iterate convergence analysis for games beyond the Euclidean settings.
  arXiv  Detail & Related papers  (2023-06-29T01:20:44Z)
• Understanding Gradient Clipping in Private SGD: A Geometric Perspective [68.61254575987013]
  Deep learning models are increasingly popular in many machine learning applications where the training data may contain sensitive information. Many learning systems now incorporate differential privacy by training their models with (differentially) private SGD. A key step in each private SGD update is gradient clipping that shrinks the gradient of an individual example whenever its L2 norm exceeds some threshold.
  arXiv  Detail & Related papers  (2020-06-27T19:08:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.