Peak detection is a problem in sequential data analysis that involves differentiating regions with higher counts (peaks) from regions with lower counts (background noise). It is crucial to correctly predict areas that deviate from the background noise, in both the train and test sets of labels. Dynamic programming changepoint algorithms have been proposed to solve the peak detection problem by constraining the mean to alternatively increase and then decrease. The current constrained changepoint algorithms only create predictions on the test set, while completely ignoring the train set. Changepoint algorithms that are both accurate when fitting the train set, and make predictions on the test set, have been proposed but not in the context of peak detection models. We propose to resolve these issues by creating a new dynamic programming algorithm, FLOPART, that has zero train label errors, and is able to provide highly accurate predictions on the test set. We provide an empirical analysis that shows FLOPART has a similar time complexity while being more accurate than the existing algorithms in terms of train and test label errors.

In this paper, we consider privacy aspects of wireless federated learning (FL) with Over-the-Air (OtA) transmission of gradient updates from multiple users/agents to an edge server. By exploiting the waveform superposition property of multiple access channels, OtA FL enables the users to transmit their updates simultaneously with linear processing techniques, which improves resource efficiency. However, this setting is vulnerable to privacy leakage since an adversary node can hear directly the uncoded message. Traditional perturbation-based methods provide privacy protection while sacrificing the training accuracy due to the reduced signal-to-noise ratio. In this work, we aim at minimizing privacy leakage to the adversary and the degradation of model accuracy at the edge server at the same time. More explicitly, spatially correlated perturbations are added to the gradient vectors at the users before transmission. Using the zero-sum property of the correlated perturbations, the side effect of the added perturbation on the aggregated gradients at the edge server can be minimized. In the meanwhile, the added perturbation will not be canceled out at the adversary, which prevents privacy leakage. Theoretical analysis of the perturbation covariance matrix, differential privacy, and model convergence is provided, based on which an optimization problem is formulated to jointly design the covariance matrix and the power scaling factor to balance between privacy protection and convergence performance. Simulation results validate the correlated perturbation approach can provide strong defense ability while guaranteeing high learning accuracy.

We propose topology-aware feature partitioning into $k$ disjoint partitions for given scene features as a method for object-centric representation learning. To this end, we propose to use minimum $s$-$t$ graph cuts as a partitioning method which is represented as a linear program. The method is topologically aware since it explicitly encodes neighborhood relationships in the image graph. To solve the graph cuts our solution relies on an efficient, scalable, and differentiable quadratic programming approximation. Optimizations specific to cut problems allow us to solve the quadratic programs and compute their gradients significantly more efficiently compared with the general quadratic programming approach. Our results show that our approach is scalable and outperforms existing methods on object discovery tasks with textured scenes and objects.

In recent years, decentralized bilevel optimization problems have received In recent years, fueled by the rise of machine learning and artificial increasing attention in the networking and machine learning intelligence in edge networks, decentralized bilevel optimization communities thanks to their versatility in modeling decentralized problems have received increasing attention in the networking and learning problems over peer-to-peer networks (e.g., multi-agent machine learning communities. This is due to the versatility of meta-learning, multi-agent reinforcement learning, personalized decentralized bilevel optimization in supporting many decentralized training, and Byzantine-resilient learning). However, for decentralized learning paradigms over peer-to-peer networks, such as the bilevel optimization over peer-to-peer networks with limited multi-agent versions of meta learning [22, 33, 33], hyperparameter computation and communication capabilities, how to achieve low optimization problem[24, 29], area under curve (AUC) problems sample and communication complexities are two fundamental challenges [19, 32], and reinforcement learning[9, 40]. To date, however, that remain under-explored so far. In this paper, we make there remain many challenges and open problems in decentralized the first attempt to investigate the class of decentralized bilevel bilevel learning over peer-to-peer networks. Two of the most optimization problems with nonconvex and strongly-convex structure fundamental challenges in decentralized bilevel optimization are corresponding to the outer and inner subproblems, respectively.

We consider the problem of learning discriminative representations for data in a high-dimensional space with distribution supported on or around multiple low-dimensional linear subspaces. That is, we wish to compute a linear injective map of the data such that the features lie on multiple orthogonal subspaces. Instead of treating this learning problem using multiple PCAs, we cast it as a sequential game using the closed-loop transcription (CTRL) framework recently proposed for learning discriminative and generative representations for general low-dimensional submanifolds. We prove that the equilibrium solutions to the game indeed give correct representations. Our approach unifies classical methods of learning subspaces with modern deep learning practice, by showing that subspace learning problems may be provably solved using the modern toolkit of representation learning. In addition, our work provides the first theoretical justification for the CTRL framework, in the important case of linear subspaces. We support our theoretical findings with compelling empirical evidence. We also generalize the sequential game formulation to more general representation learning problems. Our code, including methods for easy reproduction of experimental results, is publically available on GitHub.

Federated learning is a newly emerging paradigm for machine learning where multiple data holders (clients) collaborate to train a model on their combined dataset. Clients only share partially trained models and other statistics computed from their dataset, keeping their raw data local and private [McMahan et al., 2017, Kairouz et al., 2021]. By obviating the need for a third party to collect and store clients' data, federated learning has several advantages over the classical, centralized paradigm [Dean et al., 2012, Iandola et al., 2016, Goyal et al., 2017]: it ensures clients' consent is tied to the specific task at hand by requiring active participation of the clients in training, confers some basic level of privacy, and has the potential to make machine learning more participatory in general [Kulynych et al., 2020, Jones and Tonetti, 2020]. Further, widespread legislation of data portability and privacy requirements (such as GDPR and CCPA) might even make federated learning a necessity [Pentland et al., 2021]. Collaboration among clients is most attractive when clients have very different subsets of the combined dataset (data heterogeneity).

The robotics community has seen an exponential growth in the level of complexity of the theoretical tools presented for the modeling of soft robotics devices. Different solutions have been presented to overcome the difficulties related to the modeling of soft robots, often leveraging on other scientific disciplines, such as continuum mechanics, computational mechanics and computer graphics. These theoretical and computational foundations are often taken for granted and this leads to an intricate literature that, consequently, has rarely been the subject of a complete review. For the first time, we present here a structured overview of all the approaches proposed so far to model soft robots. The chosen classification, which is based on their theoretical and numerical grounds, allows us to provide a critical analysis about their uses and applicability. This will enable robotics researchers to learn the basics of these modeling techniques and their associated numerical methods, but also to have a critical perspective on their uses.

Bayesian optimization (BO) is a popular method for efficiently inferring optima of an expensive black-box function via a sequence of queries. Existing information-theoretic BO procedures aim to make queries that most reduce the uncertainty about optima, where the uncertainty is captured by Shannon entropy. However, an optimal measure of uncertainty would, ideally, factor in how we intend to use the inferred quantity in some downstream procedure. In this paper, we instead consider a generalization of Shannon entropy from work in statistical decision theory (DeGroot 1962, Rao 1984), which contains a broad class of uncertainty measures parameterized by a problem-specific loss function corresponding to a downstream task. We first show that special cases of this entropy lead to popular acquisition functions used in BO procedures such as knowledge gradient, expected improvement, and entropy search. We then show how alternative choices for the loss yield a flexible family of acquisition functions that can be customized for use in novel optimization settings. Additionally, we develop gradient-based methods to efficiently optimize our proposed family of acquisition functions, and demonstrate strong empirical performance on a diverse set of sequential decision making tasks, including variants of top-$k$ optimization, multi-level set estimation, and sequence search.

An optimization problem is at the heart of many robotics estimating, planning, and optimum control problems. Several attempts have been made at model-based multi-robot localization, and few have formulated the multi-robot collaborative localization problem as a factor graph problem to solve through graph optimization. Here, the optimization objective is to minimize the errors of estimating the relative location estimates in a distributed manner. Our novel graph-theoretic approach to solving this problem consists of three major components; (connectivity) graph formation, expansion through transition model, and optimization of relative poses. First, we estimate the relative pose-connectivity graph using the received signal strength between the connected robots, indicating relative ranges between them. Then, we apply a motion model to formulate graph expansion and optimize them using g$^2$o graph optimization as a distributed solver over dynamic networks. Finally, we theoretically analyze the algorithm and numerically validate its optimality and performance through extensive simulations. The results demonstrate the practicality of the proposed solution compared to a state-of-the-art algorithm for collaborative localization in multi-robot systems.

While variance reduction methods have shown great success in solving large scale optimization problems, many of them suffer from accumulated errors and, therefore, should periodically require the full gradient computation. In this paper, we present a single-loop algorithm named SLEDGE (Single-Loop mEthoD for Gradient Estimator) for finite-sum nonconvex optimization, which does not require periodic refresh of the gradient estimator but achieves nearly optimal gradient complexity. Unlike existing methods, SLEDGE has the advantage of versatility; (i) second-order optimality, (ii) exponential convergence in the PL region, and (iii) smaller complexity under less heterogeneity of data. We build an efficient federated learning algorithm by exploiting these favorable properties. We show the first and second-order optimality of the output and also provide analysis under PL conditions. When the local budget is sufficiently large and clients are less (Hessian-)~heterogeneous, the algorithm requires fewer communication rounds then existing methods such as FedAvg, SCAFFOLD, and Mime. The superiority of our method is verified in numerical experiments.