Search Results for author:
Found 5 papers, 0 papers with code
Utility-Probability Duality of Neural Networks
In this perspective, training of the neural network corresponds to a utility learning process.
Lagrangian Method for Q-Function Learning (with Applications to Machine Translation)
The paper then turns to demonstrate a symmetry breaking phenomenon regarding the optimality of the Lagrangian saddle points, which justifies a largely overlooked direction in developing the Lagrangian method.
Lagrangian Method for Episodic Learning
Our paper brings new perspectives to this general approach in the following aspects: 1) Inspired by the usually-used linear $V$-form Lagrangian, we proposed a nonlinear $Q$-form Lagrangian function and proved that it enjoys strong duality property in spite of its nonlinearity.
Simpson's Bias in NLP Training
In most machine learning tasks, we evaluate a model $M$ on a given data population $S$ by measuring a population-level metric $F(S;M)$.
Steady State Analysis of Episodic Reinforcement Learning
This paper proves that the episodic learning environment of every finite-horizon decision task has a unique steady state under any behavior policy, and that the marginal distribution of the agent's input indeed converges to the steady-state distribution in essentially all episodic learning processes.
