Pages that link to "Item:Q5854121"

The following pages link to Entropy-SGD: biasing gradient descent into wide valleys (Q5854121):

Displaying 30 items.

• Entropy-SGD (Q1354032) (← links)
• Forward stability of ResNet and its variants (Q1988347) (← links)
• Chaos and complexity from quantum neural network. A study with diffusion metric in machine learning (Q2032539) (← links)
• Bias of homotopic gradient descent for the hinge loss (Q2045131) (← links)
• On Bayesian posterior mean estimators in imaging sciences and Hamilton-Jacobi partial differential equations (Q2051535) (← links)
• Interpretable machine learning: fundamental principles and 10 grand challenges (Q2074414) (← links)
• A spin glass model for the loss surfaces of generative adversarial networks (Q2076047) (← links)
• Dimension-free log-Sobolev inequalities for mixture distributions (Q2235854) (← links)
• Deep relaxation: partial differential equations for optimizing deep neural networks (Q2319762) (← links)
• Run-and-inspect method for nonconvex optimization and global optimality bounds for R-local minimizers (Q2425163) (← links)
• Building a telescope to look into high-dimensional image spaces (Q3121213) (← links)
• Global Minima of Overparameterized Neural Networks (Q4999400) (← links)
• Entropic gradient descent algorithms and wide flat minima* (Q5020063) (← links)
• Deep networks on toroids: removing symmetries reveals the structure of flat regions in the landscape geometry* (Q5055419) (← links)
• Global Convergence of Stochastic Gradient Hamiltonian Monte Carlo for Nonconvex Stochastic Optimization: Nonasymptotic Performance Bounds and Momentum-Based Acceleration (Q5058053) (← links)
• Archetypal landscapes for deep neural networks (Q5073145) (← links)
• The inverse variance–flatness relation in stochastic gradient descent is critical for finding flat minima (Q5073270) (← links)
• Wasserstein-Based Projections with Applications to Inverse Problems (Q5074785) (← links)
• (Q5149258) (← links)
• Ensemble Kalman inversion: a derivative-free technique for machine learning tasks (Q5197869) (← links)
• Black holes and the loss landscape in machine learning (Q6061784) (← links)
• Barcodes as summary of loss function topology (Q6124396) (← links)
• Diametrical risk minimization: theory and computations (Q6134352) (← links)
• Singular perturbations in stochastic optimal control with unbounded data (Q6138481) (← links)
• Markov chain stochastic DCA and applications in deep learning with PDEs regularization (Q6143666) (← links)
• Pessimistic value iteration for multi-task data sharing in offline reinforcement learning (Q6152665) (← links)
• Model-based reinforcement learning with non-Gaussian environment dynamics and its application to portfolio optimization (Q6550745) (← links)
• Global solutions to nonconvex problems by evolution of Hamilton-Jacobi PDEs (Q6575280) (← links)
• Deep relaxation of controlled stochastic gradient descent via singular perturbations (Q6585233) (← links)
• Statistical mechanics of the maximum-average submatrix problem (Q6620193) (← links)