Learning linear non-Gaussian polytree models (UAI 2022) Daniele Tramontano, Anthea Monod, Mathias Drton [Paper]2021Online Probabilistic Label Trees (AISTATS 2021) Kalina Jasinska-Kobus, Marek Wydmuch, Devanathan Thiruvenkatachari, Krzysztof Dembczyński [Paper] [Code] Optimal Decision Trees for No...
MixUp-MIL: Novel Data Augmentation for Multiple Instance Learning and a Study on Thyroid Cancer Diagnosis Michael Gadermayr code MoCoSR: Respiratory Motion Correction and Super-Resolution for 3D Abdominal MRI Weitong Zhang code Modeling Alzheimers' Disease Progression from Multi-task and Self-supervised...
该研究使用一个序列到序列的 Transformer 架构，它有 16 个 attention head，嵌入维度为 512，总共包含 86M 个参数。像《 ‘Linear algebra with transformers 》研究中一样，研究者观察到解决这个问题的最佳架构是不对称的，解码器更深：在编码器中使用 4 层，在解码器中使用 16 层。该任务的一个显著特性是 N...
Revisiting Graph based Collaborative Filtering: A Linear Residual Graph Convolutional Network Approach. AAAI 2020. paper Lei Chen, Le Wu, Richang Hong, Kun Zhang, Meng Wang. Inductive Matrix Completion Based on Graph Neural Networks. ICLR 2020. paper Muhan Zhang, Yixin Chen. Computer Vision Graph...
(from Hao Su)8. Staying the course: Locating equilibria of dynamical systems on Riemannian manifolds defined by point-clouds. (from Ioannis G. Kevrekidis)9. Differentially Private Learning with Margin Guarantees. (from Mehryar Mohri)10. ISTRBoost: Importance Sampling Transfer Regression using Boosti...
Dist Loss: Enhancing Regression in Few-Shot Region through Distribution Distance Constraint no code yet • 20 Nov 2024 The results demonstrate that Dist Loss effectively mitigates the negative impact of imbalanced data distribution on model performance, achieving state-of-the-art results in sparse ...
and various implementation and operational issues are discussed. Properties of the estimators of the regression coefficients are evaluated through Monte Carlo experiments and compared with other procedures. The performance of this novel family of models is also illustrated on artificial and real data, wit...
7. AI Feynman 2.0: Pareto-optimal symbolic regression exploiting graph modularity. (from Silviu-Marian Udrescu, Andrew Tan, Jiahai Feng, Orisvaldo Neto, Tailin Wu, Max Tegmark) 8. On Reward-Free Reinforcement Learning with Linear Function Approximation. (from Ruosong Wang, Simon S. Du, Lin...
7. AI Feynman 2.0: Pareto-optimal symbolic regression exploiting graph modularity. (from Silviu-Marian Udrescu, Andrew Tan, Jiahai Feng, Orisvaldo Neto, Tailin Wu, Max Tegmark) 8. On Reward-Free Reinforcement Learning with Linear Function Approximation. (from Ruosong Wang, Simon S. Du, Lin ...
form the best linear forecasts for future volatility we find that the behavioral model generates sensible forecasts that get close to those of a standard GARCH(1,1) model in their overall performance, and often provide useful information on top of the information incorporated in the GARCH ...