Introduces transductive linear bandit problem; proposes an algorithm matching the information-theoretic lower bound with instance-dependent sample complexity.

Tanner Fiez, Lalit Jain, Kevin Jamieson et al.

Introduces DPP-based kernel quadrature leveraging spectral properties, achieving error bounds tied to kernel eigenvalues, outperforming classical methods.

Ayoub Belhadji, Rémi Bardenet, Pierre Chainais

Using adversarial robustness as a prior, the paper achieves near-invertible, interpretable feature representations with improved visualization and manipulation, surpassing standard models.

Logan Engstrom, Andrew Ilyas, Shibani Santurkar et al.

Study the inductive bias of neural tangent kernels, analyzing smoothness and stability in convolutional networks.

Alberto Bietti, Julien Mairal

GraphNVP employs invertible normalizing flows for molecular graph generation, decomposing structure and attributes, achieving high validity and uniqueness with exact likelihood maximization.

Kaushalya Madhawa, Katushiko Ishiguro, Kosuke Nakago et al.

Proposes an efficient Weingarten map estimator with proven asymptotic convergence rate, applied to curvature estimation and point cloud simplification.

Yueqi Cao, Didong Li, Huafei Sun et al.

Graph neural networks perform low-pass filtering, lacking nonlinear manifold learning.

Hoang NT, Takanori Maehara

DeepGLO combines global matrix factorization with local TCNs, addressing scale variance and global dependencies in high-dimensional time series forecasting.

Rajat Sen, Hsiang-Fu Yu, Inderjit Dhillon

Provides a comprehensive review of Sequential Monte Carlo (SMC) algorithms for Bayesian inference, focusing on proposal and intermediate target design, with theoretical and practical insights.

Christian A. Naesseth, Fredrik Lindsten, Thomas B. Schön

Incorporates long-term future info via latent variables, boosting long-horizon prediction and planning in model-based RL.

Nan Rosemary Ke, Amanpreet Singh, Ahmed Touati et al.

Dimension-free mean-field bounds for two-layer neural networks; kernel limit analysis reveals early kernel ridge regression behavior.

Song Mei, Theodor Misiakiewicz, Andrea Montanari

Proposes Fused Gromov-Wasserstein distance combining feature and structure, with proven metric and interpolation properties.

Titouan Vayer, Laetita Chapel, Rémi Flamary et al.

Proposes NNARS, a near-minimax optimal adaptive rejection sampling algorithm with theoretical guarantees and improved rejection rates.

Juliette Achdou, Joseph C. Lam, Alexandra Carpentier et al.

Using sparse covers and ℓ1 path variation, the paper proves deep Ramp networks can achieve risk of order √(L³ log d/n).

Andrew R. Barron, Jason M. Klusowski

Unified framework for multi-target prediction, enhancing prediction accuracy.

Willem Waegeman, Krzysztof Dembczynski, Eyke Huellermeier

Deep InfoMax (DIM) maximizes mutual information between input and high-level representations, leveraging local structures and adversarial prior matching, achieving state-of-the-art unsupervised classification.

R Devon Hjelm, Alex Fedorov, Samuel Lavoie-Marchildon et al.

Proposes two supervised topic models using stochastic variational inference to improve classification and regression accuracy.

Filipe Rodrigues, Mariana Lourenço, Bernardete Ribeiro et al.

Proposes adversarial regularization via min-max game to ensure membership privacy in deep neural networks, reducing inference attack success to near random guess with minimal utility loss.

Milad Nasr, Reza Shokri, Amir Houmansadr

Review of Gaussian processes and kernel methods, highlighting their equivalences in regression, sample paths, and dependence measures.

Motonobu Kanagawa, Philipp Hennig, Dino Sejdinovic et al.

Proposes PRD, a distribution metric separating quality and coverage, improving evaluation of generative models.

Mehdi S. M. Sajjadi, Olivier Bachem, Mario Lucic et al.