We advance a general theory of coherent preference that surrenders restrictions embodied in orthodox doctrine. This theory enjoys the property that any preference system admits extension to a complete system of preferences, provided it satisfies a certain coherence requirement analogous to the one de Finetti advanced for his foundations of probability. Unlike de Finetti's theory, the one we set forth requires neither transitivity nor Archimedeanness nor boundedness nor continuity of preference. This theory also enjoys the property that any complete preference system meeting the standard of coherence can be represented by utility in an ordered field extension of the reals. Representability by utility is a corollary of this paper's central result, which at once extends H older's Theorem and strengthens Hahn's Embedding Theorem.

Representing and quantifying Minimal Residual Disease (MRD) in Acute Myeloid Leukemia (AML), a type of cancer that affects the blood and bone marrow, is essential in the prognosis and follow-up of AML patients. As traditional cytological analysis cannot detect leukemia cells below 5\%, the analysis of flow cytometry dataset is expected to provide more reliable results. In this paper, we explore statistical learning methods based on optimal transport (OT) to achieve a relevant low-dimensional representation of multi-patient flow cytometry measurements (FCM) datasets considered as high-dimensional probability distributions. Using the framework of OT, we justify the use of the K-means algorithm for dimensionality reduction of multiple large-scale point clouds through mean measure quantization by merging all the data into a single point cloud. After this quantization step, the visualization of the intra and inter-patients FCM variability is carried out by embedding low-dimensional quantized probability measures into a linear space using either Wasserstein Principal Component Analysis (PCA) through linearized OT or log-ratio PCA of compositional data. Using a publicly available FCM dataset and a FCM dataset from Bordeaux University Hospital, we demonstrate the benefits of our approach over the popular kernel mean embedding technique for statistical learning from multiple high-dimensional probability distributions. We also highlight the usefulness of our methodology for low-dimensional projection and clustering patient measurements according to their level of MRD in AML from FCM. In particular, our OT-based approach allows a relevant and informative two-dimensional representation of the results of the FlowSom algorithm, a state-of-the-art method for the detection of MRD in AML using multi-patient FCM.

We consider the problem of approximating a function in a general nonlinear subset of $L^2$, when only a weighted Monte Carlo estimate of the $L^2$-norm can be computed. Of particular interest in this setting is the concept of sample complexity, the number of sample points that are necessary to achieve a prescribed error with high probability. Reasonable worst-case bounds for this quantity exist only for particular model classes, like linear spaces or sets of sparse vectors. For more general sets, like tensor networks or neural networks, the currently existing bounds are very pessimistic. By restricting the model class to a neighbourhood of the best approximation, we can derive improved worst-case bounds for the sample complexity. When the considered neighbourhood is a manifold with positive local reach, its sample complexity can be estimated by means of the sample complexities of the tangent and normal spaces and the manifold's curvature.

Deep convolutional networks have spectacular applications to classification and regression (LeCun et al., 2015), but they are a black box which are hard to analyze mathematically because of their architecture Despite its simplicity, it applies to complex image classification and reaches a higher accuracy than AlexNet (Krizhevsky et al., 2012) over ImageNet ILSVRC2012. It is implemented with a deep convolutional network architecture. Dictionary learning for classification was introduced in Mairal et al. (2009) and implemented with deep A major issue is to compute the sparse code with a small network. We introduce a new architecture based on homotopy continuation, which leads to exponential convergence. The ALIST A (Liu et al., 2019) sparse code is incorporated in We explain the implementation and mathematical properties of each element of the sparse scattering network.

Depth-First Branch and Bound (DFBnB) is an anytime algorithm for solving combinatorial optimization problems. In this paper we present a weighted version of DFBnB, wDFBnB, which incorporates standard techniques for using weights in heuristic search and offers suboptimality guarantees. Our main contribution drawn from a preliminary evaluation is the observation that wDFBnB, used along with automated or hand-crafted weight schedules, can significantly outperform DFBnB both in terms of anytime behavior and convergence to the optimal. We think this small study calls for more research on the design of automated weight schedules that could provide superior anytime performance across a wider range of domains.

Bounded suboptimal search algorithms are usually faster than optimal ones, but they can still run out of memory on large problems. This paper makes three contributions. First, we show how solution length estimates, used by the current state-of-the-art linear-space bounded suboptimal search algorithm Iterative Deepening EES, can be used to improve unbounded-space suboptimal search. Second, we convert one of these improved algorithms into a linear-space variant called Iterative Deepening A* epsilon, resulting in a new state of the art in linear-space bounded suboptimal search. Third, we show how Recursive Best-First Search can be used to create additional linear-space variants that have more stable performance. Taken together, these results significantly expand our armamentarium of bounded suboptimal search algorithms.

Many problems can be formulated as recovering a low-rank tensor. Although an increasingly common task, tensor recovery remains a challenging problem because of the delicacy associated with the decomposition of higher order tensors. To overcome these difficulties, existing approaches often proceed by unfolding tensors into matrices and then apply techniques for matrix completion. We show here that such matricization fails to exploit the tensor structure and may lead to suboptimal procedure. More specifically, we investigate a convex optimization approach to tensor completion by directly minimizing a tensor nuclear norm and prove that this leads to an improved sample size requirement. To establish our results, we develop a series of algebraic and probabilistic techniques such as characterization of subdifferetial for tensor nuclear norm and concentration inequalities for tensor martingales, which may be of independent interests and could be useful in other tensor related problems.

It is commonly appreciated that solving search problems optimally can overrun time and memory constraints. Bounded suboptimal search algorithms trade increased solution cost for reduced solving time and memory consumption. However, even suboptimal search can overrun memory on large problems. The conventional approach to this problem is to combine a weighted admissible heuristic with an optimal linear space algorithm, resulting in algorithms such as Weighted IDA* (wIDA*). However, wIDA* does not exploit distance-to-go estimates or inadmissible heuristics, which have recently been shown to be helpful for suboptimal search. In this paper, we present a linear space analogue of Explicit Estimation Search (EES), a recent algorithm specifically designed for bounded suboptimal search. We call our method Iterative Deepening EES (IDEES). In an empirical evaluation, we show that IDEES dramatically outperforms wIDA* on domains with non-uniform edge costs and can scale to problems that are out of reach for the original EES.

We consider the problem of reinforcement learning in high-dimensional spaces when the number of features is bigger than the number of samples. In particular, we study the least-squares temporal difference (LSTD) learning algorithm when a space of low dimension is generated with a random projection from a high-dimensional space. We provide a thorough theoretical analysis of the LSTD with random projections and derive performance bounds for the resulting algorithm. We also show how the error of LSTD with random projections is propagated through the iterations of a policy iteration algorithm and provide a performance bound for the resulting least-squares policy iteration (LSPI) algorithm.