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 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.

Proposed the Entire Space Multi-Task Model (ESMM), achieving a 2.56% AUC improvement on Taobao dataset.

Xiao Ma, Liqin Zhao, Guan Huang et al.

Proposes distributional dynamics (DD) as a PDE framework to analyze SGD in two-layer neural networks, proving convergence in large-scale limits.

Song Mei, Andrea Montanari, Phan-Minh Nguyen

Transformer-based attention model trained with REINFORCE and greedy rollout baseline, achieving near-optimal solutions for TSP and VRP with node counts up to 100, outperforming previous learned heuristics.

Wouter Kool, Herke van Hoof, Max Welling

Learn unknown ODE models using Gaussian processes to infer dynamics from sparse data and predict future states.

Markus Heinonen, Cagatay Yildiz, Henrik Mannerström et al.

Proposes NO TEARS, a continuous optimization framework for DAG structure learning using matrix exponential-based smooth constraints, outperforming traditional combinatorial methods.

Xun Zheng, Bryon Aragam, Pradeep Ravikumar et al.

Efficient numerical methods for optimal transport enable scalable high-dimensional distribution matching, benefiting image processing and machine learning.

Gabriel Peyré, Marco Cuturi

Proposed Fast Geometric Ensembling (FGE) improves accuracy by 0.56% on CIFAR-10.

Timur Garipov, Pavel Izmailov, Dmitrii Podoprikhin et al.