迄今为止，迄今为止，众所周知，对广泛的互补临床相关任务进行了全面比较了医学图像登记方法。这限制了采用研究进展，以防止竞争方法的公平基准。在过去五年内已经探讨了许多新的学习方法，但优化，建筑或度量战略的问题非常适合仍然是开放的。 Learn2reg涵盖了广泛的解剖学：脑，腹部和胸部，方式：超声波，CT，MRI，群体：患者内部和患者内部和监督水平。我们为3D注册的培训和验证建立了较低的入境障碍，这帮助我们从20多个独特的团队中汇编了65多个单独的方法提交的结果。我们的互补度量集，包括稳健性，准确性，合理性和速度，使得能够独特地位了解当前的医学图像登记现状。进一步分析监督问题的转移性，偏见和重要性，主要是基于深度学习的方法的优越性，并将新的研究方向开放到利用GPU加速的常规优化的混合方法。

通常用于深度学习的陡峭血液算法，使用梯度作为下降方向，或者在使用预处理方向偏移之后。在许多场景中，计算梯度由于复杂或非可微分的成本函数而具有数值困难，特别是奇异点旁边。在这项工作中，我们专注于常见于无监督成本职能的总变化半规范的推导。具体而言，我们在新颖的迭代方案中推导出对硬L1平滑度约束的可分辨率代理，我们称之为成本展开。在培训期间产生更准确的梯度，我们的方法通过改进的收敛来实现给定DNN模型的更精细预测，而无需修改其架构或增加计算复杂性。我们在无监督的光学流任务中展示了我们的方法。在培训众所周知的基线训练期间，更换L1平滑度限制，我们报告了对MPI Sintel和Kitti 2015无监督的光学流量基准的改进结果。特别是，我们报告EPE在封闭像素上减少了高达15.82％的，其中平滑度约束是显性的，使得能够检测更加清晰的运动边缘。

KL-regularized reinforcement learning from expert demonstrations has proved successful in improving the sample efficiency of deep reinforcement learning algorithms, allowing them to be applied to challenging physical real-world tasks. However, we show that KL-regularized reinforcement learning with behavioral reference policies derived from expert demonstrations can suffer from pathological training dynamics that can lead to slow, unstable, and suboptimal online learning. We show empirically that the pathology occurs for commonly chosen behavioral policy classes and demonstrate its impact on sample efficiency and online policy performance. Finally, we show that the pathology can be remedied by non-parametric behavioral reference policies and that this allows KL-regularized reinforcement learning to significantly outperform state-of-the-art approaches on a variety of challenging locomotion and dexterous hand manipulation tasks.

State-of-the-art language models are often accurate on many question-answering benchmarks with well-defined questions. Yet, in real settings questions are often unanswerable without asking the user for clarifying information. We show that current SotA models often do not ask the user for clarification when presented with imprecise questions and instead provide incorrect answers or "hallucinate". To address this, we introduce CLAM, a framework that first uses the model to detect ambiguous questions, and if an ambiguous question is detected, prompts the model to ask the user for clarification. Furthermore, we show how to construct a scalable and cost-effective automatic evaluation protocol using an oracle language model with privileged information to provide clarifying information. We show that our method achieves a 20.15 percentage point accuracy improvement over SotA on a novel ambiguous question-answering answering data set derived from TriviaQA.

Learned classifiers should often possess certain invariance properties meant to encourage fairness, robustness, or out-of-distribution generalization. However, multiple recent works empirically demonstrate that common invariance-inducing regularizers are ineffective in the over-parameterized regime, in which classifiers perfectly fit (i.e. interpolate) the training data. This suggests that the phenomenon of ``benign overfitting," in which models generalize well despite interpolating, might not favorably extend to settings in which robustness or fairness are desirable. In this work we provide a theoretical justification for these observations. We prove that -- even in the simplest of settings -- any interpolating learning rule (with arbitrarily small margin) will not satisfy these invariance properties. We then propose and analyze an algorithm that -- in the same setting -- successfully learns a non-interpolating classifier that is provably invariant. We validate our theoretical observations on simulated data and the Waterbirds dataset.

Selecting subsets of features that differentiate between two conditions is a key task in a broad range of scientific domains. In many applications, the features of interest form clusters with similar effects on the data at hand. To recover such clusters we develop DiSC, a data-driven approach for detecting groups of features that differentiate between conditions. For each condition, we construct a graph whose nodes correspond to the features and whose weights are functions of the similarity between them for that condition. We then apply a spectral approach to compute subsets of nodes whose connectivity differs significantly between the condition-specific feature graphs. On the theoretical front, we analyze our approach with a toy example based on the stochastic block model. We evaluate DiSC on a variety of datasets, including MNIST, hyperspectral imaging, simulated scRNA-seq and task fMRI, and demonstrate that DiSC uncovers features that better differentiate between conditions compared to competing methods.

Graphons are general and powerful models for generating graphs of varying size. In this paper, we propose to directly model graphons using neural networks, obtaining Implicit Graphon Neural Representation (IGNR). Existing work in modeling and reconstructing graphons often approximates a target graphon by a fixed resolution piece-wise constant representation. Our IGNR has the benefit that it can represent graphons up to arbitrary resolutions, and enables natural and efficient generation of arbitrary sized graphs with desired structure once the model is learned. Furthermore, we allow the input graph data to be unaligned and have different sizes by leveraging the Gromov-Wasserstein distance. We first demonstrate the effectiveness of our model by showing its superior performance on a graphon learning task. We then propose an extension of IGNR that can be incorporated into an auto-encoder framework, and demonstrate its good performance under a more general setting of graphon learning. We also show that our model is suitable for graph representation learning and graph generation.

Offline reinforcement-learning (RL) algorithms learn to make decisions using a given, fixed training dataset without the possibility of additional online data collection. This problem setting is captivating because it holds the promise of utilizing previously collected datasets without any costly or risky interaction with the environment. However, this promise also bears the drawback of this setting. The restricted dataset induces subjective uncertainty because the agent can encounter unfamiliar sequences of states and actions that the training data did not cover. Moreover, inherent system stochasticity further increases uncertainty and aggravates the offline RL problem, preventing the agent from learning an optimal policy. To mitigate the destructive uncertainty effects, we need to balance the aspiration to take reward-maximizing actions with the incurred risk due to incorrect ones. In financial economics, modern portfolio theory (MPT) is a method that risk-averse investors can use to construct diversified portfolios that maximize their returns without unacceptable levels of risk. We integrate MPT into the agent's decision-making process to present a simple-yet-highly-effective risk-aware planning algorithm for offline RL. Our algorithm allows us to systematically account for the \emph{estimated quality} of specific actions and their \emph{estimated risk} due to the uncertainty. We show that our approach can be coupled with the Transformer architecture to yield a state-of-the-art planner for offline RL tasks, maximizing the return while significantly reducing the variance.

One of the challenges currently facing the quantum computing community is the design of quantum circuits which can efficiently run on near-term quantum computers, known as the quantum compiling problem. Algorithms such as the Variational Quantum Eigensolver (VQE), Quantum Approximate Optimization Algorithm (QAOA), and Quantum Architecture Search (QAS) have been shown to generate or find optimal near-term quantum circuits. However, these methods are computationally expensive and yield little insight into the circuit design process. In this paper, we propose Quantum Deep Dreaming (QDD), an algorithm that generates optimal quantum circuit architectures for specified objectives, such as ground state preparation, while providing insight into the circuit design process. In QDD, we first train a neural network to predict some property of a quantum circuit (such as VQE energy). Then, we employ the Deep Dreaming technique on the trained network to iteratively update an initial circuit to achieve a target property value (such as ground state VQE energy). Importantly, this iterative updating allows us to analyze the intermediate circuits of the dreaming process and gain insights into the circuit features that the network is modifying during dreaming. We demonstrate that QDD successfully generates, or 'dreams', circuits of six qubits close to ground state energy (Transverse Field Ising Model VQE energy) and that dreaming analysis yields circuit design insights. QDD is designed to optimize circuits with any target property and can be applied to circuit design problems both within and outside of quantum chemistry. Hence, QDD lays the foundation for the future discovery of optimized quantum circuits and for increased interpretability of automated quantum algorithm design.

政策梯度方法被广泛用于学习控制政策。它们可以轻松地分配给多名工人，并在许多领域中达到最新结果。不幸的是，它们表现出很大的差异，随后遭受了高样本的复杂性，因为它们在整个轨迹上汇总了梯度。在另一个极端情况下，计划方法，例如树木搜索，使用考虑未来LookAhead的单步过渡来优化策略。这些方法主要用于基于价值的算法。基于计划的算法需要一个正向模型，并且在每个步骤上都是计算密集型的，但更有效。在这项工作中，我们介绍了SoftTreemax，这是将树搜索整合到策略梯度中的第一种方法。传统上，针对单个状态行动对计算梯度。取而代之的是，我们基于树的策略结构在每个环境步骤中利用树叶的所有梯度。这使我们能够将梯度的差异减少三个数量级，并与标准策略梯度相比，从更好的样本复杂性中受益。在Atari上，与分布式PPO相比，SoftTreemax在运行时的表现高达5倍。