Search Results for author:
Found 9 papers, 1 papers with code
Non-asymptotic Convergence of Discrete-time Diffusion Models: New Approach and Improved Rate
In this paper, we establish the convergence guarantee for substantially larger classes of distributions under discrete-time diffusion models and further improve the convergence rate for distributions with bounded support.
Achieving Sample and Computational Efficient Reinforcement Learning by Action Space Reduction via Grouping
To address this issue, we formulate a general optimization problem for determining the optimal grouping strategy, which strikes a balance between performance loss and sample/computational complexity.
Generalization Performance of Transfer Learning: Overparameterized and Underparameterized Regimes
For example, when the total number of features in the source task's learning model is fixed, we show that it is more advantageous to allocate a greater number of redundant features to the task-specific part rather than the common part.
Achieving Fairness in Multi-Agent Markov Decision Processes Using Reinforcement Learning
Fairness plays a crucial role in various multi-agent systems (e. g., communication networks, financial markets, etc.).
Theoretical Characterization of the Generalization Performance of Overfitted Meta-Learning
However, due to the uniqueness of meta-learning such as task-specific gradient descent inner training and the diversity/fluctuation of the ground-truth signals among training tasks, we find new and interesting properties that do not exist in single-task linear regression.
Theory on Forgetting and Generalization of Continual Learning
In particular, there is a lack of understanding on what factors are important and how they affect "catastrophic forgetting" and generalization performance.
On the Generalization Power of the Overfitted Three-Layer Neural Tangent Kernel Model
Our upper bound reveals that, between the two hidden-layers, the test error descends faster with respect to the number of neurons in the second hidden-layer (the one closer to the output) than with respect to that in the first hidden-layer (the one closer to the input).
On the Generalization Power of Overfitted Two-Layer Neural Tangent Kernel Models
Specifically, for a class of learnable functions, we provide a new upper bound of the generalization error that approaches a small limiting value, even when the number of neurons $p$ approaches infinity.
Overfitting Can Be Harmless for Basis Pursuit, But Only to a Degree
Under a sparse true linear regression model with $p$ i. i. d.
