Using input-output Jacobian norm as a sensitivity metric, the study finds strong correlation with neural network generalization across architectures and datasets.

Roman Novak, Yasaman Bahri, Daniel A. Abolafia et al.

Introduces Oblivious-Greedy for non-submodular maximization under element removal, achieving constant-factor approximation for support selection and variance reduction.

Ilija Bogunovic, Junyao Zhao, Volkan Cevher

FactorVAE improves disentanglement over β-VAE by encouraging factorial representation distribution.

Hyunjik Kim, Andriy Mnih

UMAP leverages Riemannian geometry and topology to produce scalable, high-quality low-dimensional embeddings that preserve both local and global data structures.

Leland McInnes, John Healy, James Melville

This paper clarifies bias issues in MMD-GAN training, introduces Kernel Inception Distance for evaluation, and demonstrates improved stability and efficiency.

Mikołaj Bińkowski, Danica J. Sutherland, Michael Arbel et al.

Proposes a noise-tolerant loss function based on Mean Absolute Error (MAE), theoretically proven to enable risk minimization to learn true classifiers under label noise in multi-class classification.

Aritra Ghosh, Himanshu Kumar, P. S. Sastry

Introduces Concept Activation Vectors (CAV) and TCAV to quantify high-level concept importance in neural networks, validated on image and medical datasets, demonstrating interpretability and bias detection.

Been Kim, Martin Wattenberg, Justin Gilmer et al.

Introduces bi-stochastic kernels for diffusion processes on manifolds, deriving their infinitesimal generators and heat kernel connections, with spectral and Nyström analysis.

Nicholas F. Marshall, Ronald R. Coifman

Proposes a two-step approach: stochastic dual OT plan learning and neural network Monge map approximation, applied to domain adaptation and generative modeling.

Vivien Seguy, Bharath Bhushan Damodaran, Rémi Flamary et al.

Variational Walkback learns non-equilibrium transition operators to generate samples, excelling on datasets like MNIST.

Anirudh Goyal, Nan Rosemary Ke, Surya Ganguli et al.

Proposes SNPE, a neural network-based ABC method for full Bayesian inference of neural models, accurately recovering parameters and handling missing data.

Jan-Matthis Lueckmann, Pedro J. Goncalves, Giacomo Bassetto et al.

Proves gradient descent on separable data converges directionally to max-margin (hard margin SVM) solution with rate O(1/ log t).

Daniel Soudry, Elad Hoffer, Mor Shpigel Nacson et al.

Proposed a new estimator combining logistic regression and Kullback-Leibler distance to efficiently estimate conversion probability on Criteo dataset.

Abdollah Safari, Rachel MacKay Altman, Thomas M. Loughin

Deep Wasserstein embedding (DWE) learns neural network-based Euclidean approximation of W2 distance, enabling fast large-scale distribution analysis.

Nicolas Courty, Rémi Flamary, Mélanie Ducoffe

Proposed LinGapE, a fully adaptive linear bandit pure exploration algorithm with near-optimal sample complexity.

Liyuan Xu, Junya Honda, Masashi Sugiyama

Gradual pruning method reduces large models by up to 10x with minimal accuracy loss, outperforming small dense models of same size.

Michael Zhu, Suyog Gupta

Proposed a crowd layer for end-to-end deep learning from noisy labels, outperforming EM and voting methods with specific datasets.

Filipe Rodrigues, Francisco Pereira

A non-parametric conditional independence test based on nearest-neighbor conditional mutual information estimation, offering superior calibration and efficiency in high-dimensional, nonlinear settings.

Jakob Runge

Robust statistical methods (e.g., MCD, LTS, PCA) effectively detect outliers in high-dimensional data, improving robustness and interpretability.

Peter J. Rousseeuw, Mia Hubert

DARLA significantly improves zero-shot transfer in RL by learning disentangled representations, achieving a 270.3% performance boost.

Irina Higgins, Arka Pal, Andrei A. Rusu et al.