To overcome this challenge, diverging from conventional efforts of expanding the solver's search scope, we focus on enabling information to actively propagate to the solver through heat diffusion.

We find that it significantly improves the base systems'

Homomorphic encryption (HE)-based deep neural network (DNN) inference protects data and model privacy but suffers from significant computation overhead. We observe transforming the DNN weights into circulant matrices converts general matrix-vector multiplications into HE-friendly 1-dimensional convolutions, drastically reducing the HE computation cost.

Multi-task learning is a promising paradigm for handling several tasks simultaneously using a unified architecture.

Through extensive empirical analysis using benchmarks in the Safety Gym suite, we show that our algorithm has similar or better performance than SoT A (non-episodic) algorithms adapted for the episodic setting.

When artificial agents are jointly trained to perform collaborative tasks using a communication channel, they develop opaque goal-oriented communication protocols.

For example, in personalized medical diagnostics, a model is built based on historical data to facilitate an optimal treatment for a new patient (Bica et al., 2021).

Interpretability work in machine learning (ML) seeks to develop tools that make models more intelligible to humans in order to better monitor model behavior and predict failure modes. Early work in interpretability sought to identify relationships between model outputs and input features (Ribeiro et al., 2016; Covert et al., 2022), but with only black-box query access to observe inputs and outputs, it can be difficult to evaluate a model's internal logic.

Imitation learning (IL) aims to recover the expert behavior from the dataset of demonstrations.