Search Results for author:
Found 10 papers, 1 papers with code
Efficient LLM inference solution on Intel GPU
A customized Scaled-Dot-Product-Attention kernel is designed to match our fusion policy based on the segment KV cache solution.
FedCBO: Reaching Group Consensus in Clustered Federated Learning through Consensus-based Optimization
Federated learning is an important framework in modern machine learning that seeks to integrate the training of learning models from multiple users, each user having their own local data set, in a way that is sensitive to data privacy and to communication loss constraints.
Continuous-in-time Limit for Bayesian Bandits
The optimal policy for the limiting HJB equation can be explicitly obtained for several common bandit problems, and we give numerical methods to solve the HJB equation when an explicit solution is not available.
On Large Batch Training and Sharp Minima: A Fokker-Planck Perspective
We study the statistical properties of the dynamic trajectory of stochastic gradient descent (SGD).
Operator Shifting for Model-based Policy Evaluation
When the error is in the residual norm, we prove that the shifting factor is always positive and upper bounded by $1+O\left(1/n\right)$, where $n$ is the number of samples used in learning each row of the transition matrix.
Model-based Reinforcement Learning
reinforcement-learning
+1
Variational Actor-Critic Algorithms
The objective function of the variational formulation consists of two parts: one for maximizing the value function and the other for minimizing the Bellman residual.
A Note on Optimization Formulations of Markov Decision Processes
This note summarizes the optimization formulations used in the study of Markov decision processes.
Optimization and Control
Why resampling outperforms reweighting for correcting sampling bias with stochastic gradients
We consider two commonly-used techniques, resampling and reweighting, that rebalance the proportions of the subgroups to maintain the desired objective function.
Borrowing From the Future: Addressing Double Sampling in Model-free Control
The main idea is to borrow extra randomness from the future to approximately re-sample the next state when the underlying dynamics of the problem are sufficiently smooth.
Towards Theoretical Understanding of Large Batch Training in Stochastic Gradient Descent
In particular, we give an explicit escaping time of SGD from a local minimum in the finite-time regime and prove that SGD tends to converge to flatter minima in the asymptotic regime (although may take exponential time to converge) regardless of the batch size.
