尽管自我监督学习（SSL）方法取得了经验成功，但尚不清楚其表示的哪些特征导致了高下游精度。在这项工作中，我们表征了SSL表示应该满足的属性。具体而言，我们证明了必要和充分的条件，因此，对于给出的数据增强的任何任务，在该表示形式上训练的所需探针（例如，线性或MLP）具有完美的准确性。这些要求导致一个统一的概念框架，用于改善现有的SSL方法并得出新方法。对于对比度学习，我们的框架规定了对以前的方法（例如使用不对称投影头）的简单但重大改进。对于非对比度学习，我们使用框架来得出一个简单新颖的目标。我们所得的SSL算法在标准基准测试上的表现优于基线，包括Imagenet线性探测的SHAV+多螺旋桨。

剪辑的发展[Radford等，2021]引发了关于语言监督是否可以导致与传统仅图像方法更可转移表示的视觉模型的争论。我们的工作通过对两种方法的学习能力进行了对下游分类任务的学习能力进行仔细控制的比较来研究这个问题。我们发现，当预训练数据集符合某些标准时 - 它足够大，并且包含具有较低变异性的描述性字幕 - 仅图像的方法也与剪辑的传输性能不匹配，即使它们接受了更多图像数据的培训。但是，与人们期望的相反，在某些情况下，没有满足这些标准，其中通过标题增加的监督实际上是有害的。在我们的发现的激励下，我们设计了简单的处方，以使剪辑能够更好地利用现有预训练数据集中存在的语言信息。

机器学习系统经常在培训和测试之间遇到分发转变。在本文中，我们介绍了一个简单的变分目标，其OptiCa正好成为所有表现形式的集合，在那种情况下，保证风险最小化者对保留贝叶斯预测因子的任何分配换档，例如协变量。我们的目标有两个组成部分。首先，表示必须保持对任务的判别，即，一些预测指标必须能够同时最小化来源和目标风险。其次，代表性的边际支持需要跨源头和目标相同。我们通过设计自我监督的学习方法来实现这一实用，只使用未标记的数据和增强来培训强大的陈述。我们的目标在域底实现最先进的结果，并对最近的方法（如剪辑）的稳健性提供洞察力。

This short study reformulates the statistical Bayesian learning problem using a quantum mechanics framework. Density operators representing ensembles of pure states of sample wave functions are used in place probability densities. We show that such representation allows to formulate the statistical Bayesian learning problem in different coordinate systems on the sample space. We further show that such representation allows to learn projections of density operators using a kernel trick. In particular, the study highlights that decomposing wave functions rather than probability densities, as it is done in kernel embedding, allows to preserve the nature of probability operators. Results are illustrated with a simple example using discrete orthogonal wavelet transform of density operators.

Graph Neural Networks (GNNs) have shown great potential in the field of graph representation learning. Standard GNNs define a local message-passing mechanism which propagates information over the whole graph domain by stacking multiple layers. This paradigm suffers from two major limitations, over-squashing and poor long-range dependencies, that can be solved using global attention but significantly increases the computational cost to quadratic complexity. In this work, we propose an alternative approach to overcome these structural limitations by leveraging the ViT/MLP-Mixer architectures introduced in computer vision. We introduce a new class of GNNs, called Graph MLP-Mixer, that holds three key properties. First, they capture long-range dependency and mitigate the issue of over-squashing as demonstrated on the Long Range Graph Benchmark (LRGB) and the TreeNeighbourMatch datasets. Second, they offer better speed and memory efficiency with a complexity linear to the number of nodes and edges, surpassing the related Graph Transformer and expressive GNN models. Third, they show high expressivity in terms of graph isomorphism as they can distinguish at least 3-WL non-isomorphic graphs. We test our architecture on 4 simulated datasets and 7 real-world benchmarks, and show highly competitive results on all of them.

We study inductive matrix completion (matrix completion with side information) under an i.i.d. subgaussian noise assumption at a low noise regime, with uniform sampling of the entries. We obtain for the first time generalization bounds with the following three properties: (1) they scale like the standard deviation of the noise and in particular approach zero in the exact recovery case; (2) even in the presence of noise, they converge to zero when the sample size approaches infinity; and (3) for a fixed dimension of the side information, they only have a logarithmic dependence on the size of the matrix. Differently from many works in approximate recovery, we present results both for bounded Lipschitz losses and for the absolute loss, with the latter relying on Talagrand-type inequalities. The proofs create a bridge between two approaches to the theoretical analysis of matrix completion, since they consist in a combination of techniques from both the exact recovery literature and the approximate recovery literature.

We introduce MegaPose, a method to estimate the 6D pose of novel objects, that is, objects unseen during training. At inference time, the method only assumes knowledge of (i) a region of interest displaying the object in the image and (ii) a CAD model of the observed object. The contributions of this work are threefold. First, we present a 6D pose refiner based on a render&compare strategy which can be applied to novel objects. The shape and coordinate system of the novel object are provided as inputs to the network by rendering multiple synthetic views of the object's CAD model. Second, we introduce a novel approach for coarse pose estimation which leverages a network trained to classify whether the pose error between a synthetic rendering and an observed image of the same object can be corrected by the refiner. Third, we introduce a large-scale synthetic dataset of photorealistic images of thousands of objects with diverse visual and shape properties and show that this diversity is crucial to obtain good generalization performance on novel objects. We train our approach on this large synthetic dataset and apply it without retraining to hundreds of novel objects in real images from several pose estimation benchmarks. Our approach achieves state-of-the-art performance on the ModelNet and YCB-Video datasets. An extensive evaluation on the 7 core datasets of the BOP challenge demonstrates that our approach achieves performance competitive with existing approaches that require access to the target objects during training. Code, dataset and trained models are available on the project page: https://megapose6d.github.io/.

When searching for policies, reward-sparse environments often lack sufficient information about which behaviors to improve upon or avoid. In such environments, the policy search process is bound to blindly search for reward-yielding transitions and no early reward can bias this search in one direction or another. A way to overcome this is to use intrinsic motivation in order to explore new transitions until a reward is found. In this work, we use a recently proposed definition of intrinsic motivation, Curiosity, in an evolutionary policy search method. We propose Curiosity-ES, an evolutionary strategy adapted to use Curiosity as a fitness metric. We compare Curiosity with Novelty, a commonly used diversity metric, and find that Curiosity can generate higher diversity over full episodes without the need for an explicit diversity criterion and lead to multiple policies which find reward.

Deep Neural Networks (DNNs) outshine alternative function approximators in many settings thanks to their modularity in composing any desired differentiable operator. The formed parametrized functional is then tuned to solve a task at hand from simple gradient descent. This modularity comes at the cost of making strict enforcement of constraints on DNNs, e.g. from a priori knowledge of the task, or from desired physical properties, an open challenge. In this paper we propose the first provable affine constraint enforcement method for DNNs that requires minimal changes into a given DNN's forward-pass, that is computationally friendly, and that leaves the optimization of the DNN's parameter to be unconstrained i.e. standard gradient-based method can be employed. Our method does not require any sampling and provably ensures that the DNN fulfills the affine constraint on a given input space's region at any point during training, and testing. We coin this method POLICE, standing for Provably Optimal LInear Constraint Enforcement.

Shapley values are ubiquitous in interpretable Machine Learning due to their strong theoretical background and efficient implementation in the SHAP library. Computing these values previously induced an exponential cost with respect to the number of input features of an opaque model. Now, with efficient implementations such as Interventional TreeSHAP, this exponential burden is alleviated assuming one is explaining ensembles of decision trees. Although Interventional TreeSHAP has risen in popularity, it still lacks a formal proof of how/why it works. We provide such proof with the aim of not only increasing the transparency of the algorithm but also to encourage further development of these ideas. Notably, our proof for Interventional TreeSHAP is easily adapted to Shapley-Taylor indices and one-hot-encoded features.