Asia
Understanding, Predicting and Better Resolving Q-Value Divergence in Offline-RL Y ang Yue
We also give unique insights into its effectiveness.
Optimal Unbiased Randomizers for Regression with Label Differential Privacy
We propose a new family of label randomizers for training regression models under the constraint of label differential privacy (DP).
MALL T
Among all the contributing factors, the quality and selection of data is becoming increasingly recognized for its importance in training LLMs effectively.
Model Reconstruction Using Counterfactual Explanations: A Perspective From Polytope Theory
An adversary may be able to "steal" the model by querying for counterfactuals and training a
Binarized Neural Machine Translation
The rapid scaling of language models is motivating research using low-bitwidth quantization. In this work, we propose a novel binarization technique for Transformers applied to machine translation (BMT), the first of its kind.
Revisiting Implicit Differentiation for Learning Problems in Optimal Control
In contrast, we directly evaluate the matrix equations which arise from applying variable elimination on the Lagrange multiplier terms in the (differential) KKT system.
