Considering generating samples with high rewards, we focus on optimizing deep neural networks parameterized stochastic differential equations (SDEs), the advanced generative models with high expressiveness, with policy gradient, the leading algorithm in reinforcement learning. Nevertheless, when applying policy gradients to SDEs, since the policy gradient is estimated on a finite set of trajectories, it can be ill-defined, and the policy behavior in data-scarce regions may be uncontrolled. This challenge compromises the stability of policy gradients and negatively impacts sample complexity. To address these issues, we propose constraining the SDE to be consistent with its associated perturbation process. Since the perturbation process covers the entire space and is easy to sample, we can mitigate the aforementioned problems. Our framework offers a general approach allowing for a versatile selection of policy gradient methods to effectively and efficiently train SDEs. We evaluate our algorithm on the task of structure-based drug design and optimize the binding affinity of generated ligand molecules. Our method achieves the best Vina score (-9.07) on the CrossDocked2020 dataset.

Machine learning force fields (MLFFs) have instigated a groundbreaking shift in molecular dynamics (MD) simulations across a wide range of fields, such as physics, chemistry, biology, and materials science. Incorporating higher order many-body interactions can enhance the expressiveness and accuracy of models. Recent models have achieved this by explicitly including up to four-body interactions. However, five-body interactions, which have relevance in various fields, are still challenging to incorporate efficiently into MLFFs. In this work, we propose the quintuple network (QuinNet), an end-to-end graph neural network that efficiently expresses many-body interactions up to five-body interactions with \emph{ab initio} accuracy. By analyzing the topology of diverse many-body interactions, we design the model architecture to efficiently and explicitly represent these interactions. We evaluate QuinNet on public datasets of small molecules, such as MD17 and its revised version, and show that it is compatible with other state-of-the-art models on these benchmarks. Moreover, QuinNet surpasses many leading models on larger and more complex molecular systems, such as MD22 and Chignolin, without increasing the computational complexity. We also use QuinNet as a force field for molecular dynamics (MD) simulations to demonstrate its accuracy and stability, and conduct an ablation study to elucidate the significance of five-body interactions. We open source our implementation at https://github.com/Zun-Wang/QuinNet.

The problem of online learning with graph feedback has been extensively studied in the literature due to its generality and potential to model various learning tasks. Existing works mainly study the adversarial and stochastic feedback separately. If the prior knowledge of the feedback mechanism is unavailable or wrong, such specially designed algorithms could suffer great loss. To avoid this problem, \citet{erez2021towards} try to optimize for both environments. However, they assume the feedback graphs are undirected and each vertex has a self-loop, which compromises the generality of the framework and may not be satisfied in applications. With a general feedback graph, the observation of an arm may not be available when this arm is pulled, which makes the exploration more expensive and the algorithms more challenging to perform optimally in both environments. In this work, we overcome this difficulty by a new trade-off mechanism with a carefully-designed proportion for exploration and exploitation. We prove the proposed algorithm simultaneously achieves $\mathrm{poly} \log T$ regret in the stochastic setting and minimax-optimal regret of $\tilde{O}(T^{2/3})$ in the adversarial setting where $T$ is the horizon and $\tilde{O}$ hides parameters independent of $T$ as well as logarithmic terms. To our knowledge, this is the first best-of-both-worlds result for general feedback graphs.

Noisy labeled data is more a norm than a rarity for crowd sourced contents. It is effective to distill noise and infer correct labels through aggregating results from crowd workers. To ensure the time relevance and overcome slow responses of workers, online label aggregation is increasingly requested, calling for solutions that can incrementally infer true label distribution via subsets of data items. In this paper, we propose a novel online label aggregation framework, BiLA , which employs variational Bayesian inference method and designs a novel stochastic optimization scheme for incremental training. BiLA is flexible to accommodate any generating distribution of labels by the exact computation of its posterior distribution. We also derive the convergence bound of the proposed optimizer. We compare BiLA with the state of the art based on minimax entropy, neural networks and expectation maximization algorithms, on synthetic and real-world data sets. Our evaluation results on various online scenarios show that BiLA can effectively infer the true labels, with an error rate reduction of at least 10 to 1.5 percent points for synthetic and real-world datasets, respectively.

Exploration and exploitation trade-off is one of the key concerns in reinforcement learning. Previous work on one-player Markov Decision Processes has reached near-optimal results for both PAC and high probability regret guarantees. However, such an analysis is lacking for the more complex stochastic games with multi-players, where all players aim to find an approximate Nash Equilibrium. In this work, we address the exploration issue for the $N$-player finite-horizon turn-based stochastic games (FTSG). We propose a framework, \textit{Upper Bounding the Values for Players} (UBVP), to guide exploration in FTSGs. UBVP leverages the key insight that players choose the optimal policy conditioning on the policies of the others simultaneously; thus players can explore \textit{in the face of uncertainty} and get close to the Nash Equilibrium. Based on UBVP, we present two provable algorithms. One is \textit{Uniform}-PAC with a sample complexity of $\tilde{O}(1/\epsilon^2)$ to get an $\epsilon$-Nash Equilibrium for arbitrary $\epsilon>0$, and the other has a cumulative exploitability of $\tilde{O}(\sqrt{T})$ with high probability.

To deal with the low qualities of web workers in crowdsourcing, many unsupervised label aggregation methods have been investigated but most of them provide inconsistent performance. In this paper, we explore the learning from crowds with selective verification problem. In addition to the noisy responses from the crowds, it also collects the ground truths for a well-chosen subset of tasks as the reference, then aggregates the redundant responses based on the patterns provided by both the supervised and unsupervised signal. To improve the labeling efficiency, we propose the EBM selecting strategy for choosing the verification subset, which is based on the loss error minimization. Specifically, we first establish the expected loss error given the semi-supervised learning estimate, then find the subset that minimizes this selecting criterion. We do extensive empirical comparisons on both synthetic and real-world datasets to show the benefits of this new learning setting as well as our proposal.

Thompson sampling has impressive empirical performance for many multi-armed bandit problems. But current algorithms for Thompson sampling only work for the case of conjugate priors since they require to perform online Bayesian posterior inference, which is a difficult task when the prior is not conjugate. In this paper, we propose a novel algorithm for Thompson sampling which only requires to draw samples from a tractable proposal distribution. So our algorithm is efficient even when the prior is non-conjugate. To do this, we reformulate Thompson sampling as an optimization proplem via the Gumbel-Max trick. After that we construct a set of random variables and our goal is to identify the one with highest mean which is an instance of best arm identification problems. Finally, we solve it with techniques in best arm identification. Experiments show that our algorithm works well in practice.

We study the problem on how to learn the pure Nash Equilibrium of a two-player zero-sum static game with random payoffs under unknown distributions via efficient payoff queries. We introduce a multi-armed bandit model to this problem due to its ability to find the best arm efficiently among random arms and propose two algorithms for this problem—LUCB-G based on the confidence bounds and a racing algorithm based on successive action elimination. We provide an analysis on the sample complexity lower bound when the Nash Equilibrium exists.