[كتاب][B] Control systems and reinforcement learning
S Meyn - 2022 - books.google.com
A high school student can create deep Q-learning code to control her robot, without any
understanding of the meaning of'deep'or'Q', or why the code sometimes fails. This book is …
understanding of the meaning of'deep'or'Q', or why the code sometimes fails. This book is …
On the optimization of deep networks: Implicit acceleration by overparameterization
Conventional wisdom in deep learning states that increasing depth improves
expressiveness but complicates optimization. This paper suggests that, sometimes …
expressiveness but complicates optimization. This paper suggests that, sometimes …
Acceleration methods
This monograph covers some recent advances in a range of acceleration techniques
frequently used in convex optimization. We first use quadratic optimization problems to …
frequently used in convex optimization. We first use quadratic optimization problems to …
Stochastic gradient descent performs variational inference, converges to limit cycles for deep networks
Stochastic gradient descent (SGD) is widely believed to perform implicit regularization when
used to train deep neural networks, but the precise manner in which this occurs has thus far …
used to train deep neural networks, but the precise manner in which this occurs has thus far …
[HTML][HTML] User-friendly guarantees for the Langevin Monte Carlo with inaccurate gradient
In this paper, we study the problem of sampling from a given probability density function that
is known to be smooth and strongly log-concave. We analyze several methods of …
is known to be smooth and strongly log-concave. We analyze several methods of …
Understanding the acceleration phenomenon via high-resolution differential equations
Gradient-based optimization algorithms can be studied from the perspective of limiting
ordinary differential equations (ODEs). Motivated by the fact that existing ODEs do not …
ordinary differential equations (ODEs). Motivated by the fact that existing ODEs do not …
Underdamped Langevin MCMC: A non-asymptotic analysis
We study the underdamped Langevin diffusion when the log of the target distribution is
smooth and strongly concave. We present a MCMC algorithm based on its discretization and …
smooth and strongly concave. We present a MCMC algorithm based on its discretization and …
Acceleration by stepsize hedging: Multi-step descent and the silver stepsize schedule
Can we accelerate the convergence of gradient descent without changing the algorithm—
just by judiciously choosing stepsizes? Surprisingly, we show that the answer is yes. Our …
just by judiciously choosing stepsizes? Surprisingly, we show that the answer is yes. Our …
Accelerated gradient descent escapes saddle points faster than gradient descent
Nesterov's accelerated gradient descent (AGD), an instance of the general family of
“momentum methods,” provably achieves faster convergence rate than gradient descent …
“momentum methods,” provably achieves faster convergence rate than gradient descent …
Stochastic modified equations and adaptive stochastic gradient algorithms
We develop the method of stochastic modified equations (SME), in which stochastic gradient
algorithms are approximated in the weak sense by continuous-time stochastic differential …
algorithms are approximated in the weak sense by continuous-time stochastic differential …