亚洲男人的天堂2018av,欧美草比,久久久久久免费视频精选,国色天香在线看免费,久久久久亚洲av成人片仓井空

We develop a flexible stochastic approximation framework for analyzing the long-run behavior of learning in games (both continuous and finite). The proposed analysis template incorporates a wide array of popular learning algorithms, including gradient-based methods, the exponential/multiplicative weights algorithm for learning in finite games, optimistic and bandit variants of the above, etc. In addition to providing an integrated view of these algorithms, our framework further allows us to obtain several new convergence results, both asymptotic and in finite time, in both continuous and finite games. Specifically, we provide a range of criteria for identifying classes of Nash equilibria and sets of action profiles that are attracting with high probability, and we also introduce the notion of coherence, a game-theoretic property that includes strict and sharp equilibria, and which leads to convergence in finite time. Importantly, our analysis applies to both oracle-based and bandit, payoff-based methods - that is, when players only observe their realized payoffs.

The focus of this work is sample-efficient deep reinforcement learning (RL) with a simulator. One useful property of simulators is that it is typically easy to reset the environment to a previously observed state. We propose an algorithmic framework, named uncertainty-first local planning (UFLP), that takes advantage of this property. Concretely, in each data collection iteration, with some probability, our meta-algorithm resets the environment to an observed state which has high uncertainty, instead of sampling according to the initial-state distribution. The agent-environment interaction then proceeds as in the standard online RL setting. We demonstrate that this simple procedure can dramatically improve the sample cost of several baseline RL algorithms on difficult exploration tasks. Notably, with our framework, we can achieve super-human performance on the notoriously hard Atari game, Montezuma's Revenge, with a simple (distributional) double DQN. Our work can be seen as an efficient approximate implementation of an existing algorithm with theoretical guarantees, which offers an interpretation of the positive empirical results.

Federated Learning (FL) enables multiple clients to collaboratively learn a machine learning model without exchanging their own local data. In this way, the server can exploit the computational power of all clients and train the model on a larger set of data samples among all clients. Although such a mechanism is proven to be effective in various fields, existing works generally assume that each client preserves sufficient data for training. In practice, however, certain clients may only contain a limited number of samples (i.e., few-shot samples). For example, the available photo data taken by a specific user with a new mobile device is relatively rare. In this scenario, existing FL efforts typically encounter a significant performance drop on these clients. Therefore, it is urgent to develop a few-shot model that can generalize to clients with limited data under the FL scenario. In this paper, we refer to this novel problem as federated few-shot learning. Nevertheless, the problem remains challenging due to two major reasons: the global data variance among clients (i.e., the difference in data distributions among clients) and the local data insufficiency in each client (i.e., the lack of adequate local data for training). To overcome these two challenges, we propose a novel federated few-shot learning framework with two separately updated models and dedicated training strategies to reduce the adverse impact of global data variance and local data insufficiency. Extensive experiments on four prevalent datasets that cover news articles and images validate the effectiveness of our framework compared with the state-of-the-art baselines. Our code is provided at //github.com/SongW-SW/F2L.

Learning from demonstrations (LfD) enables humans to easily teach collaborative robots (cobots) new motions that can be generalized to new task configurations without retraining. However, state-of-the-art LfD methods require manually tuning intrinsic parameters and have rarely been used in industrial contexts without experts. We propose a parameter-free LfD method based on probabilistic movement primitives, where parameters are determined using Jensen-Shannon divergence and Bayesian optimization, and users do not have to perform manual parameter tuning. The cobot's precision in reproducing learned motions, and its ease of teaching and use by non-expert users are evaluated in two field tests. In the first field test, the cobot works on elevator door maintenance. In the second test, three factory workers teach the cobot tasks useful for their daily workflow. Errors between the cobot and target joint angles are insignificant -- at worst $0.28$ deg -- and the motion is accurately reproduced -- GMCC score of 1. Questionnaires completed by the workers highlighted the method's ease of use and the accuracy of the reproduced motion. Our code and recorded trajectories are made available online.

Randomized controlled trials (RCTs) are the gold standard for causal inference, but they are often powered only for average effects, making estimation of heterogeneous treatment effects (HTEs) challenging. Conversely, large-scale observational studies (OS) offer a wealth of data but suffer from confounding bias. Our paper presents a novel framework to leverage OS data for enhancing the efficiency in estimating conditional average treatment effects (CATEs) from RCTs while mitigating common biases. We propose an innovative approach to combine RCTs and OS data, expanding the traditionally used control arms from external sources. The framework relaxes the typical assumption of CATE invariance across populations, acknowledging the often unaccounted systematic differences between RCT and OS participants. We demonstrate this through the special case of a linear outcome model, where the CATE is sparsely different between the two populations. The core of our framework relies on learning potential outcome means from OS data and using them as a nuisance parameter in CATE estimation from RCT data. We further illustrate through experiments that using OS findings reduces the variance of the estimated CATE from RCTs and can decrease the required sample size for detecting HTEs.

Hypernetworks, neural networks that predict the parameters of another neural network, are powerful models that have been successfully used in diverse applications from image generation to multi-task learning. Unfortunately, existing hypernetworks are often challenging to train. Training typically converges far more slowly than for non-hypernetwork models, and the rate of convergence can be very sensitive to hyperparameter choices. In this work, we identify a fundamental and previously unidentified problem that contributes to the challenge of training hypernetworks: a magnitude proportionality between the inputs and outputs of the hypernetwork. We demonstrate both analytically and empirically that this can lead to unstable optimization, thereby slowing down convergence, and sometimes even preventing any learning. We present a simple solution to this problem using a revised hypernetwork formulation that we call Magnitude Invariant Parametrizations (MIP). We demonstrate the proposed solution on several hypernetwork tasks, where it consistently stabilizes training and achieves faster convergence. Furthermore, we perform a comprehensive ablation study including choices of activation function, normalization strategies, input dimensionality, and hypernetwork architecture; and find that MIP improves training in all scenarios. We provide easy-to-use code that can turn existing networks into MIP-based hypernetworks.

Coverage path planning is the problem of finding the shortest path that covers the entire free space of a given confined area, with applications ranging from robotic lawn mowing and vacuum cleaning, to demining and search-and-rescue tasks. While offline methods can find provably complete, and in some cases optimal, paths for known environments, their value is limited in online scenarios where the environment is not known beforehand, especially in the presence of non-static obstacles. We propose an end-to-end reinforcement learning-based approach in continuous state and action space, for the online coverage path planning problem that can handle unknown environments. We construct the observation space from both global maps and local sensory inputs, allowing the agent to plan a long-term path, and simultaneously act on short-term obstacle detections. To account for large-scale environments, we propose to use a multi-scale map input representation. Furthermore, we propose a novel total variation reward term for eliminating thin strips of uncovered space in the learned path. To validate the effectiveness of our approach, we perform extensive experiments in simulation with a distance sensor, surpassing the performance of a recent reinforcement learning-based approach.

Neural networks are very effective when trained on large datasets for a large number of iterations. However, when they are trained on non-stationary streams of data and in an online fashion, their performance is reduced (1) by the online setup, which limits the availability of data, (2) due to catastrophic forgetting because of the non-stationary nature of the data. Furthermore, several recent works (Caccia et al., 2022; Lange et al., 2023) arXiv:2205.1345(2) showed that replay methods used in continual learning suffer from the stability gap, encountered when evaluating the model continually (rather than only on task boundaries). In this article, we study the effect of model ensembling as a way to improve performance and stability in online continual learning. We notice that naively ensembling models coming from a variety of training tasks increases the performance in online continual learning considerably. Starting from this observation, and drawing inspirations from semi-supervised learning ensembling methods, we use a lightweight temporal ensemble that computes the exponential moving average of the weights (EMA) at test time, and show that it can drastically increase the performance and stability when used in combination with several methods from the literature.

With the rapid increase of large-scale, real-world datasets, it becomes critical to address the problem of long-tailed data distribution (i.e., a few classes account for most of the data, while most classes are under-represented). Existing solutions typically adopt class re-balancing strategies such as re-sampling and re-weighting based on the number of observations for each class. In this work, we argue that as the number of samples increases, the additional benefit of a newly added data point will diminish. We introduce a novel theoretical framework to measure data overlap by associating with each sample a small neighboring region rather than a single point. The effective number of samples is defined as the volume of samples and can be calculated by a simple formula $(1-\beta^{n})/(1-\beta)$, where $n$ is the number of samples and $\beta \in [0,1)$ is a hyperparameter. We design a re-weighting scheme that uses the effective number of samples for each class to re-balance the loss, thereby yielding a class-balanced loss. Comprehensive experiments are conducted on artificially induced long-tailed CIFAR datasets and large-scale datasets including ImageNet and iNaturalist. Our results show that when trained with the proposed class-balanced loss, the network is able to achieve significant performance gains on long-tailed datasets.

Sufficient training data is normally required to train deeply learned models. However, the number of pedestrian images per ID in person re-identification (re-ID) datasets is usually limited, since manually annotations are required for multiple camera views. To produce more data for training deeply learned models, generative adversarial network (GAN) can be leveraged to generate samples for person re-ID. However, the samples generated by vanilla GAN usually do not have labels. So in this paper, we propose a virtual label called Multi-pseudo Regularized Label (MpRL) and assign it to the generated images. With MpRL, the generated samples will be used as supplementary of real training data to train a deep model in a semi-supervised learning fashion. Considering data bias between generated and real samples, MpRL utilizes different contributions from predefined training classes. The contribution-based virtual labels are automatically assigned to generated samples to reduce ambiguous prediction in training. Meanwhile, MpRL only relies on predefined training classes without using extra classes. Furthermore, to reduce over-fitting, a regularized manner is applied to MpRL to regularize the learning process. To verify the effectiveness of MpRL, two state-of-the-art convolutional neural networks (CNNs) are adopted in our experiments. Experiments demonstrate that by assigning MpRL to generated samples, we can further improve the person re-ID performance on three datasets i.e., Market-1501, DukeMTMCreID, and CUHK03. The proposed method obtains +6.29%, +6.30% and +5.58% improvements in rank-1 accuracy over a strong CNN baseline respectively, and outperforms the state-of-the- art methods.