We appreciate the valuable comments and positive feedback from the reviewers. Without averaging the iterates, no convergence rate is available. In this paper we consider neural network with one hidden layer. In particular, Proposition 4.7 shows that neural TD attains the global minimum of MSBE (without the We will revise the "without loss of generality" claim in the revision. We will clarify this notation in the revision.

We appreciate the valuable comments and positive feedback from the reviewers. Without averaging the iterates, no convergence rate is available. In particular, Proposition 4.7 shows that neural TD attains the global minimum of MSBE (without the We will revise the "without loss of generality" claim in the revision. We will clarify this notation in the revision. We will fix them in the revision.

Neural Information Processing Systems http://nips.cc/

Molecular conformer generation is a fundamental task in computational chemistry. The objective is to predict stable low-energy 3D molecular structures, known as conformers, given the 2D molecule. Accurate molecular conformations are crucial for various applications that depend on precise spatial and geometric qualities, including drug discovery and protein docking. We introduce CoarsenConf, an SE(3)-equivariant hierarchical variational autoencoder (VAE) that pools information from fine-grain atomic coordinates to a coarse-grain subgraph level representation for efficient autoregressive conformer generation. Coarse-graining reduces the dimensionality of the problem allowing conditional autoregressive generation rather than generating all coordinates independently, as done in prior work.

The AAAI 2023 best paper awards were presented at the conference on Saturday 11 February. The awards comprised one outstanding paper, one outstanding student paper, and 12 distinguished papers. The AAAI outstanding paper award is given to a paper (or papers) that "exemplifies the highest standards in technical contribution and exposition". Abstract: The aim of Inverse Reinforcement Learning (IRL) is to infer a reward function R from a policy pi. To do this, we need a model of how pi relates to R. In the current literature, the most common models are optimality, Boltzmann rationality, and causal entropy maximisation.

The Genetic and Evolutionary Computation Conference (GECCO 2023) will present the latest high-quality results in genetic and evolutionary computation. Topics include genetic algorithms, genetic programming, ant colony optimization and swarm intelligence, complex systems, evolutionary combinatorial optimization and metaheuristics, evolutionary machine learning, evolutionary multiobjective optimization, evolutionary numerical optimization, neuroevolution, real world applications, search-based software engineering, theory, hybrids and more. The full list of tracks is available. The GECCO 2023 Program Committee invites the submission of technical papers describing your best work in genetic and evolutionary computation. Full papers of at most 8 pages (excluding references) should present original work that meets the high-quality standards of GECCO.