The problem of online linear regression is considered from an individual sequence perspective, where the aim is to control the square loss predictive regret with respect to the best linear predictor \theta \top x_t simultaneously for every sequence of covariate vectors x_t \in R d and outcomes y_t \in R in some constraint set. This is naturally formulated as a sequential game between the forecaster and an adversarial environment. In previous work [1], this problem was addressed in the "fixed-design" case, where the horizon T and the sequence of covariate vectors x_1 T is known in advance. The exact minimax strategy (MMS) was introduced and shown to be minimax optimal under natural constraint sets on the label sequence (such as ellipse-constrained labels). The MMS strategy consists in some form of least squares, but where the inverse cumulative covariance matrix \Pi_t {-1} is replaced by a shrunk version P_t that takes future instance into account.

Function-as-a-Service (FaaS) is a growing cloud computing paradigm that is expected to reduce the user cost of service over traditional serverful approaches. However, the environmental impact of FaaS has not received much attention. We investigate FaaS scheduling and scaling from a sustainability perspective in this work. We find that the service-level objectives (SLOs) of FaaS and carbon emissions conflict with each other. We also find that SLO-focused FaaS scheduling can exacerbate water use in a datacenter. We propose a novel sustainability-focused FaaS scheduling and scaling framework to co-optimize SLO performance, carbon emissions, and wastewater generation.

Dense Convolutional Network has been continuously refined to adopt a highly efficient and compact architecture, owing to its lightweight and efficient structure. However, the current Dense-like architectures are mainly designed manually, it becomes increasingly difficult to adjust the channels and reuse level based on past experience. As such, we propose an architecture search method called Dense Optimizer that can search high-performance dense-like network automatically. In Dense Optimizer, we view the dense network as a hierarchical information system, maximize the network's information entropy while constraining the distribution of the entropy across each stage via a power law, thereby constructing an optimization problem. We also propose a branch-and-bound optimization algorithm, tightly integrates power-law principle with search space scaling to solve the optimization problem efficiently. The superiority of Dense Optimizer has been validated on different computer vision benchmark datasets. Specifically, Dense Optimizer completes high-quality search but only costs 4 hours with one CPU. Our searched model DenseNet-OPT achieved a top 1 accuracy of 84.3% on CIFAR-100, which is 5.97% higher than the original one.

This paper introduces a novel classification for Autonomous Mobile Robots (AMRs), into three phases and five steps, focusing on autonomous collision-free navigation. Additionally, it presents the main methods and widely accepted technologies for each phase of the proposed classification. The purpose of this classification is to facilitate understanding and establish connections between the independent input variables of the system (hardware, software) and autonomous navigation. By analyzing well-established technologies in terms of sensors and methods used for autonomous navigation, this paper aims to provide a foundation of knowledge that can be applied in future projects of mobile robots.

Faithfulness is arguably the most critical metric to assess the reliability of explainable AI. In NLP, current methods for faithfulness evaluation are fraught with discrepancies and biases, often failing to capture the true reasoning of models. We introduce Adversarial Sensitivity as a novel approach to faithfulness evaluation, focusing on the explainer's response when the model is under adversarial attack. Our method accounts for the faithfulness of explainers by capturing sensitivity to adversarial input changes. This work addresses significant limitations in existing evaluation techniques, and furthermore, quantifies faithfulness from a crucial yet underexplored paradigm.

We consider online linear regression: at each round, an adversary reveals a covariate vector, the learner predicts a real value, the adversary reveals a label, and the learner suffers the squared prediction error. The aim is to minimize the difference between the cumulative loss and that of the linear predictor that is best in hindsight. Previous work demonstrated that the minimax optimal strategy is easy to compute recursively from the end of the game; this requires the entire sequence of covariate vectors in advance. We show that, once provided with a measure of the scale of the problem, we can invert the recursion and play the minimax strategy without knowing the future covariates. Further, we show that this forward recursion remains optimal even against adaptively chosen labels and covariates, provided that the adversary adheres to a set of constraints that prevent misrepresentation of the scale of the problem.

Bandit learning is characterized by the tension between long-term exploration and short-term exploitation. However, as has recently been noted, in settings in which the choices of the learning algorithm correspond to important decisions about individual people (such as criminal recidivism prediction, lending, and sequential drug trials), exploration corresponds to explicitly sacrificing the well-being of one individual for the potential future benefit of others. In such settings, one might like to run a greedy'' algorithm, which always makes the optimal decision for the individuals at hand --- but doing this can result in a catastrophic failure to learn. In this paper, we consider the linear contextual bandit problem and revisit the performance of the greedy algorithm. We give a smoothed analysis, showing that even when contexts may be chosen by an adversary, small perturbations of the adversary's choices suffice for the algorithm to achieve no regret'', perhaps (depending on the specifics of the setting) with a constant amount of initial training data. This suggests that in slightly perturbed environments, exploration and exploitation need not be in conflict in the linear setting.

We consider a generalization of mixed regression where the response is an additive combination of several mixture components. Standard mixed regression is a special case where each response is generated from exactly one component. Typical approaches to the mixture regression problem employ local search methods such as Expectation Maximization (EM) that are prone to spurious local optima. On the other hand, a number of recent theoretically-motivated \emph{Tensor-based methods} either have high sample complexity, or require the knowledge of the input distribution, which is not available in most of practical situations. In this work, we study a novel convex estimator \emph{MixLasso} for the estimation of generalized mixed regression, based on an atomic norm specifically constructed to regularize the number of mixture components.

Summary: This paper proposes a modification of Mondorian Forest which is a variant of Random Forest, a majority vote of decision trees. The authors show that the modified algorithm has the consistency property while the original algorithm does not have one. In particular, when the conditional probability function is Lipschitz, the proposed algorithm achieves the minimax error rate, where the lower bound is previously known. Comments: The technical contribution is to refine the original version of the Mondorian Forest and prove its consistency. The theoretical results are nice and solid. The main idea comes from the original algorithm, thus the originality of the paper is a bit incremental.

Overview and Summary This paper presents a method for motion planning where the cost of evaluating transitions between robot configurations is high. The problem is formulated as a graph-search algorithm, where the order of graph expansion has a large impact on the performance of the algorithm due to the edge expansion cost. The paper uses ideas from optimal test selection in order to derive the resulting algorithm. The algorithm is tested on a number of synthetic datasets, a simulator, and a real-world helicopter planning problem. Detailed Comments This paper extended work within the well-studied domain of robotic motion planning, extending and combining prior work in the area to construct a new algorithm.