Search Results for author:
Found 6 papers, 1 papers with code
Fast sampling from constrained spaces using the Metropolis-adjusted Mirror Langevin algorithm
This algorithm adds an accept-reject filter to the Markov chain induced by a single step of the Mirror Langevin algorithm (Zhang et al., 2020), which is a basic discretisation of the Mirror Langevin dynamics.
Sample Efficient Reinforcement Learning In Continuous State Spaces: A Perspective Beyond Linearity
Reinforcement learning (RL) is empirically successful in complex nonlinear Markov decision processes (MDPs) with continuous state spaces.
Efficient Estimators for Heavy-Tailed Machine Learning
A dramatic improvement in data collection technologies has aided in procuring massive amounts of unstructured and heterogeneous datasets.
On Learning Ising Models under Huber's Contamination Model
We study the problem of learning Ising models in a setting where some of the samples from the underlying distribution can be arbitrarily corrupted.
On the Analysis of Trajectories of Gradient Descent in the Optimization of Deep Neural Networks
Theoretical analysis of the error landscape of deep neural networks has garnered significant interest in recent years.
ADINE: An Adaptive Momentum Method for Stochastic Gradient Descent
Using this motivation, we propose our method $\textit{ADINE}$ that helps weigh the previous updates more (by setting the momentum parameter $> 1$), evaluate our proposed algorithm on deep neural networks and show that $\textit{ADINE}$ helps the learning algorithm to converge much faster without compromising on the generalization error.
