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.

BatchBALD selects diverse data points via mutual information approximation, enhancing data efficiency in deep Bayesian active learning.

Andreas Kirsch, Joost van Amersfoort, Yarin Gal

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

Ayoub Belhadji, Rémi Bardenet, Pierre Chainais

Proposes using language as an abstraction for hierarchical RL, enabling efficient learning and generalization in complex tasks.

Yiding Jiang, Shixiang Gu, Kevin Murphy et al.

Neural latent variable model for open domain event extraction, outperforming state-of-the-art on large-scale news datasets.

Xiao Liu, Heyan Huang, Yue Zhang

This study introduces a deep learning-based personalized persuasive dialogue system, achieving 59.6% F1 on a 300-sample annotated dataset, advancing social good applications.

Xuewei Wang, Weiyan Shi, Richard Kim et al.

This paper quantifies the approximation power of deep ReLU networks, establishing explicit width-depth relations achieving near-optimal rates.

Zuowei Shen, Haizhao Yang, Shijun Zhang

Proposes State Marginal Matching (SMM) for efficient exploration via a two-player game framework, improving exploration speed and adaptability.

Lisa Lee, Benjamin Eysenbach, Emilio Parisotto et al.

GluonTS is a deep learning library for probabilistic time series forecasting, supporting models like DeepAR and Transformer with comprehensive evaluation tools.

Alexander Alexandrov, Konstantinos Benidis, Michael Bohlke-Schneider et al.

FedMF combines federated learning and homomorphic encryption to enable privacy-preserving matrix factorization, validated on MovieLens 100K with comparable accuracy.

Di Chai, Leye Wang, Kai Chen et al.

SPoC employs compilation error signals for guided search, boosting long program synthesis success from 25.6% to 44.7%.

Sumith Kulal, Panupong Pasupat, Kartik Chandra et al.

Data-driven MPC based on behavioral systems theory guarantees stability and robustness without system identification.

Julian Berberich, Johannes Köhler, Matthias A. Müller et al.

This study analyzes BERT's attention heads, revealing their alignment with syntactic relations, and demonstrates dependency parsing with 77% accuracy using attention maps.

Kevin Clark, Urvashi Khandelwal, Omer Levy et al.

Proposes Differentiable Surface Splatting (DSS), a high-fidelity point cloud renderer enabling gradient-based geometry optimization, outperforming state-of-the-art in inverse rendering.

Wang Yifan, Felice Serena, Shihao Wu et al.

BIGPATENT dataset offers 1.3 million patent abstracts, advancing high-compression abstractive summarization.

Eva Sharma, Chen Li, Lu Wang

BADGE algorithm selects samples by balancing diversity and uncertainty, enhancing label efficiency in deep learning models.

Jordan T. Ash, Chicheng Zhang, Akshay Krishnamurthy et al.

Proposes substantiated perspective discovery task; constructs PERSPECTRUM dataset with 1000 claims, 10,000 perspectives, 8,000 evidence paragraphs; baseline models outperform simple methods but lag behind humans.

Sihao Chen, Daniel Khashabi, Wenpeng Yin et al.

Proposes email subject line generation using a two-stage extractive-abstractive model, trained on AESLC, outperforming baselines with ROUGE-1 score of 25.41.

Rui Zhang, Joel Tetreault

This study presents RGBD multimodal end-to-end autonomous driving, with early fusion outperforming single-modality models.

Yi Xiao, Felipe Codevilla, Akhil Gurram et al.

VAE combines deep neural networks with probabilistic inference, using reparameterization to efficiently optimize ELBO, enabling high-quality generative modeling.

Diederik P. Kingma, Max Welling