Item request has been placed! ×
Item request cannot be made. ×
loading  Processing Request
Item request has been placed! ×
Item request cannot be made. ×
loading  Processing Request
Conference

Beyond Average Return in Markov Decision Processes

Subjects: Markov Decision Process; Dynamic Programming; statistical functionnalsNew Orleans; United States

  • Source: Thirty-seventh Conference on Neural Information Processing Systems ; Neurips 2023 ; https://hal.science/hal-04264487 ; Neurips 2023, Dec 2023, New Orleans, United States

Record details

×
Conference

Full Gradient Deep Reinforcement Learning for Average-Reward Criterion

Subjects: Markov decision processes; average reward; Full Gradient DQN algorithmUnited StatesPhiladelphia, United States

  • Source: Proceedings of Machine Learning Research (PMLR) ; L4DC - The 5th Annual Learning for Dynamics and Control Conference ; https://inria.hal.science/hal-04372096 ; L4DC - The 5th Annual Learning for

Record details

×
Conference

Does a sparse ReLU network training problem always admit an optimum?

Subjects: Topology; Best Approximation Property; Sparse ReLU Neural NetworkNew Orleans (Lousiane); United States

  • Source: NeurIPS 2023 - Thirty-seventh Conference on Neural Information Processing Systems ; https://inria.hal.science/hal-04108849 ; NeurIPS 2023 - Thirty-seventh Conference on Neural Information Processing

Record details

×
Conference

Rethinking Gauss-Newton for learning over-parameterized models ; Repenser Gauss-Newton pour l'apprentissage de modèles sur-paramétrés

Subjects: Gauss Newton method; Neural netwoks; OptimizationLa Nouvelle-Orléans; United States

  • Source: NeurIPS 2023 - Thirty-seventh Conference on Neural Information Processing Systems ; https://hal.science/hal-04362139 ; NeurIPS 2023 - Thirty-seventh Conference on Neural Information Processing

Record details

×
Conference

Exploiting hidden structures in non-convex games for convergence to Nash equilibrium

Subjects: Non-convex games; Hidden games; Stochastic algorithmsNew Orleans (LA); United States

  • Source: Proceedings of the 37th International Conference on Neural Information Processing Systems ; NeurIPS 2023 - 37th Conference on Neural Information Processing Systems ;

Record details

×
Conference

Riemannian stochastic optimization methods avoid strict saddle points

Subjects: Optimization on manifolds; Stochastic approximation; Saddle-point avoidanceNew Orleans (LA); United States

  • Source: Riemannian stochastic optimization methods avoid strict saddle points ; NeurIPS 2023 - 37th Conference on Neural Information Processing Systems ;

Record details

×
  • 1-10 of  1,196 results for ""Mathematics""