Country
Supplementaryto"DSelect-k: Differentiable SelectionintheMixtureofExpertswithApplications toMulti-TaskLearning "
MTL: InMTL, deep learning-based architectures that perform soft-parameter sharing, i.e., share model parameters partially, are proving to be effective at exploiting both the commonalities and differences among tasks [6]. Ourwork is also related to [5] who introduced "routers" (similar to gates) that can choose which layers or components of layers to activate per-task. The routers in the latter work are not differentiable and requirereinforcementlearning. To construct ฮฑ, there are two cases to consider: (i)s = k and (ii) s < k. If s = k, then set ฮฑi = log(w ti) for i [k]. Our base case is fort = 1.
DiffGS: Functional Gaussian Splatting Diffusion
Y u-Shen Liu is the corresponding author.
Think Globally, Act Locally: A Deep Neural Network Approach to High-Dimensional Time Series Forecasting
Rajat Sen, Hsiang-Fu Yu, Inderjit S. Dhillon
Neural Information Processing Systems http://nips.cc/
Deep Supervised Summarization: Algorithm and Application to Learning Instructions
Chengguang Xu, Ehsan Elhamifar
Neural Information Processing Systems http://nips.cc/
DeepReinforcementLearningattheEdgeofthe StatisticalPrecipice
Research in artificial intelligence, and particularly deep reinforcement learning (RL), relies on evaluating aggregate performance on a diverse suite of tasks to assess progress.
MSAGPT: NeuralPromptingProteinStructure PredictionviaMSAGenerativePre-Training
Anillustrativeexample inFigure 1(a)showcases thatthecorrelations analysis among amino acids (AAs) sites could reveal contacts or conservative regions in the folding structure.