{"total":65,"rows":[{"id":"2111.09832","title":"Merging Models with Fisher-Weighted Averaging","created":"2021-11-18","cited_by_count":621,"area":null},{"id":"2210.08649","title":"Loss Minimization through the Lens of Outcome Indistinguishability","created":"2022-10-16","cited_by_count":62,"area":null},{"id":"2310.18554","title":"Improved Regret Bounds of (Multinomial) Logistic Bandits via Regret-to-Confidence-Set Conversion","created":"2023-10-28","cited_by_count":24,"area":null},{"id":"2102.05485","title":"On the Properties of Kullback-Leibler Divergence Between Multivariate Gaussian Distributions","created":"2021-02-10","cited_by_count":23,"area":null},{"id":"2106.05367","title":"Pulling back information geometry","created":"2021-06-09","cited_by_count":23,"area":null},{"id":"2107.04205","title":"On the Variance of the Fisher Information for Deep Learning","created":"2021-07-09","cited_by_count":22,"area":null},{"id":"2201.13094","title":"Designing Universal Causal Deep Learning Models: The Geometric (Hyper)Transformer","created":"2022-01-31","cited_by_count":22,"area":null},{"id":"2305.10491","title":"Bayesian Renormalization","created":"2023-05-17","cited_by_count":14,"area":null},{"id":"2210.08502","title":"FIT: A Metric for Model Sensitivity","created":"2022-10-16","cited_by_count":11,"area":null},{"id":"2602.15293","title":"The Information Geometry of Softmax: Probing and Steering","created":"2026-02-17","cited_by_count":11,"area":null},{"id":"2505.19371","title":"Foundations of Top-$k$ Decoding For Language Models","created":"2025-05-25","cited_by_count":10,"area":null},{"id":"2104.13289","title":"Model-centric Data Manifold: the Data Through the Eyes of the Model","created":"2021-04-26","cited_by_count":9,"area":null},{"id":"2202.11685","title":"A Class of Geometric Structures in Transfer Learning: Minimax Bounds and Optimality","created":"2022-02-23","cited_by_count":9,"area":null},{"id":"2405.17538","title":"Bayesian RG Flow in Neural Network Field Theories","created":"2024-05-27","cited_by_count":9,"area":null},{"id":"2310.01041","title":"Language Model Decoding as Direct Metrics Optimization","created":"2023-10-02","cited_by_count":8,"area":null},{"id":"2402.00944","title":"NCoder -- A Quantum Field Theory approach to encoding data","created":"2024-02-01","cited_by_count":8,"area":null},{"id":"2110.02529","title":"On the Importance of Firth Bias Reduction in Few-Shot Classification","created":"2021-10-06","cited_by_count":7,"area":null},{"id":"2203.00922","title":"Adversarial attacks on neural networks through canonical Riemannian foliations","created":"2022-03-02","cited_by_count":5,"area":null},{"id":"2203.10592","title":"Geometric Methods for Sampling, Optimisation, Inference and Adaptive Agents","created":"2022-03-20","cited_by_count":5,"area":null},{"id":"2212.03857","title":"Phase2vec: Dynamical systems embedding with a physics-informed convolutional network","created":"2022-12-07","cited_by_count":5,"area":null},{"id":"2310.01032","title":"The Fisher-Rao geometry of CES distributions","created":"2023-10-02","cited_by_count":5,"area":null},{"id":"2507.11789","title":"Enforcing Latent Euclidean Geometry in Single-Cell VAEs for Manifold Interpolation","created":"2025-07-15","cited_by_count":5,"area":null},{"id":"2105.02845","title":"A Unifying and Canonical Description of Measure-Preserving Diffusions","created":"2021-05-06","cited_by_count":4,"area":null},{"id":"2302.07612","title":"Towards Optimal Compression: Joint Pruning and Quantization","created":"2023-02-15","cited_by_count":4,"area":null},{"id":"2107.05901","title":"Fast approximations of the Jeffreys divergence between univariate Gaussian mixture models via exponential polynomial densities","created":"2021-07-13","cited_by_count":3,"area":null},{"id":"2209.07481","title":"Variational Representations of Annealing Paths: Bregman Information under Monotonic Embedding","created":"2022-09-15","cited_by_count":3,"area":null},{"id":"2306.06062","title":"Neural FIM for learning Fisher Information Metrics from point cloud data","created":"2023-06-01","cited_by_count":3,"area":null},{"id":"2312.12849","title":"Divergences induced by dual subtractive and divisive normalizations of exponential families and their convex deformations","created":"2023-12-20","cited_by_count":2,"area":null},{"id":"2107.07115","title":"Principal component analysis for Gaussian process posteriors","created":"2021-07-15","cited_by_count":1,"area":null},{"id":"2204.11278","title":"Unsupervised Learning Discriminative MIG Detectors in Nonhomogeneous Clutter","created":"2022-04-24","cited_by_count":1,"area":null},{"id":"2307.15778","title":"Spherical and Hyperbolic Toric Topology-Based Codes On Graph Embedding for Ising MRF Models: Classical and Quantum Topology Machine Learning","created":"2023-07-28","cited_by_count":1,"area":null},{"id":"2310.03884","title":"Information Geometry for the Working Information Theorist","created":"2023-10-05","cited_by_count":1,"area":null},{"id":"2402.17943","title":"Sequential transport maps using SoS density estimation and $\\alpha$-divergences","created":"2024-02-27","cited_by_count":1,"area":null},{"id":"2409.12057","title":"Cartan moving frames and the data manifolds","created":"2024-09-18","cited_by_count":1,"area":null},{"id":"2502.00846","title":"Federated Generalised Variational Inference: A Robust Probabilistic Federated Learning Framework","created":"2025-02-02","cited_by_count":1,"area":null},{"id":"2503.21128","title":"Squared families: Searching beyond regular probability models","created":"2025-03-27","cited_by_count":1,"area":null},{"id":"2506.01324","title":"Near-Optimal Clustering in Mixture of Markov Chains","created":"2025-06-02","cited_by_count":1,"area":null},{"id":"2510.04602","title":"Wasserstein Gradient Flows for Scalable and Regularized Barycenter Computation","created":"2025-10-06","cited_by_count":1,"area":null},{"id":"2602.02577","title":"Relaxed Triangle Inequality for Kullback-Leibler Divergence Between Multivariate Gaussian Distributions","created":"2026-01-31","cited_by_count":1,"area":null},{"id":"2604.09234","title":"Statistical Properties of the King Wen Sequence: An Anti-Habituation Structure That Does Not Improve Neural Network Training","created":"2026-04-10","cited_by_count":1,"area":null},{"id":"2607.01455","title":"Ember: A Kilobyte-State Optimizer for Token Interfaces","created":"2026-07-01","cited_by_count":1,"area":null},{"id":"2203.13164","title":"On the Kullback-Leibler divergence between pairwise isotropic Gaussian-Markov random fields","created":"2022-03-24","cited_by_count":0,"area":null},{"id":"2211.01306","title":"Properties of the Concrete distribution","created":"2022-11-02","cited_by_count":0,"area":null},{"id":"2306.01995","title":"Asymptotically Optimal Pure Exploration for Infinite-Armed Bandits","created":"2023-06-03","cited_by_count":0,"area":null},{"id":"2401.00953","title":"Families of costs with zero and nonnegative MTW tensor in optimal transport and the c-divergences","created":"2024-01-01","cited_by_count":0,"area":null},{"id":"2408.12961","title":"Symplectic Bregman divergences","created":"2024-08-23","cited_by_count":0,"area":null},{"id":"2502.00168","title":"Supervised Quadratic Feature Analysis: Information Geometry Approach for Dimensionality Reduction","created":"2025-01-31","cited_by_count":0,"area":null},{"id":"2508.05066","title":"Two tales for a geometric Jensen--Shannon divergence","created":"2025-08-07","cited_by_count":0,"area":null},{"id":"2510.26266","title":"A Likely Geometry of Generative Models","created":"2025-10-30","cited_by_count":0,"area":null},{"id":"2511.21741","title":"A Multiscale Geometric Method for Capturing Relational Topic Alignment","created":"2025-11-21","cited_by_count":0,"area":null},{"id":"2512.16213","title":"Enhanced 3D Shape Analysis via Information Geometry","created":"2025-12-18","cited_by_count":0,"area":null},{"id":"2602.00130","title":"On the Relationship Between Representation Geometry and Generalization in Deep Neural Networks","created":"2026-01-28","cited_by_count":0,"area":null},{"id":"2603.16088","title":"RecBundle: A Next-Generation Geometric Paradigm for Explainable Recommender Systems","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2604.11026","title":"Optimal Stability of KL Divergence under Gaussian Perturbations","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2604.24047","title":"Generalising maximum mean discrepancy: kernelised functional Bregman divergences","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2604.24083","title":"Information-Geometric First-Passage Monitoring of Distributional Stability in Stochastic Systems","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2606.14690","title":"A Complexity Measure for Active Learning in Multi-group Mean Estimation","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2606.23838","title":"The Degeneracy Distillery","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2606.29118","title":"An Information-Geometric Justification for Composite Coherence in Event-Based Narrative Extraction","created":"2026-06-28","cited_by_count":0,"area":null},{"id":"2607.03145","title":"CuBAS: Information Geometric Curvature-Based Adaptive Sampling for Supervised Classification","created":"2026-07-03","cited_by_count":0,"area":null},{"id":"2608.11724","title":"Proportional Analogies on Probability Distributions via Bayesian Updating","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2608.14220","title":"A Generalized Parallelogram Rule for Proportional Analogies on Riemannian Manifolds","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2609.22337","title":"When and Why Do Linear Bias Probes Fail? A Geometric and Statistical Theory of Bias Detectability in Large Language Model Representations","created":"2026-07-21","cited_by_count":0,"area":null},{"id":"2609.30220","title":"Riemannian Gradient Descent for Gaussian Mixture Models with unknown diagonal covariances","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.35614","title":"EvE: An Alternate Optimizer to Adam","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}