The asymptotically efficient online learning problem is investigated for stochastic censored regression models, which arise from various fields of learning and statistics but up to now still lacks comprehensive theoretical studies on the efficiency of the learning algorithms. For this, we propose a two-step online algorithm, where the first step focuses on achieving algorithm convergence, and the second step is dedicated to improving the estimation performance. Under a general excitation condition on the data, we show that our algorithm is strongly consistent and asymptotically normal by employing the stochastic Lyapunov function method and limit theories for martingales. Moreover, we show that the covariances of the estimates can achieve the Cramér-Rao(C-R) bound asymptotically, indicating that the performance of the proposed algorithm is the best possible that one can expect in general. Unlike most of the existing works, our results are obtained without resorting to the traditionally used but stringent conditions such as independent and identically distributed (i.i.d) assumption on the data, and thus our results do not exclude applications to stochastic dynamical systems with feedback. A numerical example is also provided to illustrate the superiority of the proposed online algorithm over the existing related ones in the literature. Keywords: stochastic dynamical systems, censored regression models, online learning, non-i.i.d data, cramér-Rao bound.

Solving program induction problems requires searching through an enormous space of possibilities. DreamCoder is an inductive program synthesis system that, whilst solving problems, learns to simplify search in an iterative wake-sleep procedure. The cost of search is amortised by training a neural search policy, reducing search breadth and effectively "compiling" useful information to compose program solutions across tasks. Additionally, a library of program components is learnt to express discovered solutions in fewer components, reducing search depth. In DreamCoder, the neural search policy has only an indirect effect on the library learnt through the program solutions it helps discover. We present an approach for library learning that directly leverages the neural search policy, effectively "decompiling" its amortised knowledge to extract relevant program components. This provides stronger amortised inference: the amortised knowledge learnt to reduce search breadth is now also used to reduce search depth. We integrate our approach with DreamCoder and demonstrate faster domain proficiency with improved generalisation on a range of domains, particularly when fewer example solutions are available.

In this work, we present a method to add perturbations to the code descriptions to create new inputs in natural language (NL) from well-intentioned developers that diverge from the original ones due to the use of new words or because they miss part of them. The goal is to analyze how and to what extent perturbations affect the performance of AI code generators in the context of security-oriented code. First, we show that perturbed descriptions preserve the semantics of the original, non-perturbed ones. Then, we use the method to assess the robustness of three state-of-the-art code generators against the newly perturbed inputs, showing that the performance of these AI-based solutions is highly affected by perturbations in the NL descriptions. To enhance their robustness, we use the method to perform data augmentation, i.e., to increase the variability and diversity of the NL descriptions in the training data, proving its effectiveness against both perturbed and non-perturbed code descriptions.

Language models (LMs) are becoming the foundation for almost all major language technologies, but their capabilities, limitations, and risks are not well understood. We present Holistic Evaluation of Language Models (HELM) to improve the transparency of language models. First, we taxonomize the vast space of potential scenarios (i.e. use cases) and metrics (i.e. desiderata) that are of interest for LMs. Then we select a broad subset based on coverage and feasibility, noting what's missing or underrepresented (e.g. question answering for neglected English dialects, metrics for trustworthiness). Second, we adopt a multi-metric approach: We measure 7 metrics (accuracy, calibration, robustness, fairness, bias, toxicity, and efficiency) for each of 16 core scenarios when possible (87.5% of the time). This ensures metrics beyond accuracy don't fall to the wayside, and that trade-offs are clearly exposed. We also perform 7 targeted evaluations, based on 26 targeted scenarios, to analyze specific aspects (e.g. reasoning, disinformation). Third, we conduct a large-scale evaluation of 30 prominent language models (spanning open, limited-access, and closed models) on all 42 scenarios, 21 of which were not previously used in mainstream LM evaluation. Prior to HELM, models on average were evaluated on just 17.9% of the core HELM scenarios, with some prominent models not sharing a single scenario in common. We improve this to 96.0%: now all 30 models have been densely benchmarked on the same core scenarios and metrics under standardized conditions. Our evaluation surfaces 25 top-level findings. For full transparency, we release all raw model prompts and completions publicly for further analysis, as well as a general modular toolkit. We intend for HELM to be a living benchmark for the community, continuously updated with new scenarios, metrics, and models.

Deep reinforcement learning has the potential to address various scientific problems. In this paper, we implement an optics simulation environment for reinforcement learning based controllers. The environment captures the essence of nonconvexity, nonlinearity, and time-dependent noise inherent in optical systems, offering a more realistic setting. Subsequently, we provide the benchmark results of several reinforcement learning algorithms on the proposed simulation environment. The experimental findings demonstrate the superiority of off-policy reinforcement learning approaches over traditional control algorithms in navigating the intricacies of complex optical control environments. The code of the paper is available at https://github.com/Walleclipse/Reinforcement-Learning-Pulse-Stacking.

It is widely recognized that the generalization ability of neural networks can be greatly enhanced through carefully tuning the training procedure. The current state-of-the-art training approach involves utilizing stochastic gradient descent (SGD) or Adam optimization algorithms along with a combination of additional regularization techniques such as weight decay, dropout, or noise injection. Optimal generalization can only be achieved by tuning a multitude of hyper-parameters extensively, which can be time-consuming and necessitates the additional validation dataset. To address this issue, we present a nearly tuning-free PAC-Bayes training framework that requires no extra regularization. This framework achieves test performance comparable to that of SGD/Adam, even when the latter are optimized through a complete grid search and supplemented with additional regularization terms. To understand the underlying benefits of these strategies, numerous studies have focused on studying individual strategies. For instance, it has been shown that larger learning rates (Cohen et al., 2021; Barrett & Dherin, 2020), momentum (Ghosh et al., 2022), smaller batch sizes (Lee & Jang, 2022) and batch normalization (Luo et al., 2018) individually induce higher degrees of implicit regularization on the sharpness of the loss function, yielding better generalization. Additionally, the intensity of explicit regularization techniques such as weight decay (Loshchilov & Hutter, 2017), dropout (Wei et al., 2020), parameter noise injection (Neelakantan et al., 2015; Orvieto et al., 2022), label noise (Damian et al., 2021) can significantly affect generalization. Despite these observations and explanations, it's unclear why seeking optimal combinations of these regularizations is still crucial in practice. Adjusting the intensity of each regularization based on different scenarios can be a tedious job, especially when previous research has indicated that some techniques can conflict with each other (Li et al., 2019). We summarize this challenge for conventional training in (Q1). Alternatively, PAC-Bayes generalization bounds provide foundational insights into generalization in the absence of validation and testing data (Shawe-Taylor & Williamson, 1997). Jiang et al. (2019) further suggests that PAC-Bayes bounds are among the best for evaluating generalization capabilities. Although PAC-Bayes bounds were traditionally used only in the post-training stage for quality control (Vapnik, 1998; McAllester, 1999), the recent work (Dziugaite & Roy, 2017b) has opened the door to using these bounds during the training phase. They showed that one can directly train a network via optimizing the PAC-Bayes bound, a strategy we refer to as PAC-Bayes training, and obtain reasonable performances.

Most existing federated learning methods are unable to estimate model/predictive uncertainty since the client models are trained using the standard loss function minimization approach which ignores such uncertainties. In many situations, however, especially in limited data settings, it is beneficial to take into account the uncertainty in the model parameters at each client as it leads to more accurate predictions and also because reliable estimates of uncertainty can be used for tasks, such as out-of-distribution (OOD) detection, and sequential decision-making tasks, such as active learning. We present a framework for federated learning with uncertainty where, in each round, each client infers the posterior distribution over its parameters as well as the posterior predictive distribution (PPD), distills the PPD into a single deep neural network, and sends this network to the server. Unlike some of the recent Bayesian approaches to federated learning, our approach does not require sending the whole posterior distribution of the parameters from each client to the server but only the PPD in the distilled form as a deep neural network. In addition, when making predictions at test time, it does not require computationally expensive Monte-Carlo averaging over the posterior distribution because our approach always maintains the PPD in the form of a single deep neural network. Moreover, our approach does not make any restrictive assumptions, such as the form of the clients' posterior distributions, or of their PPDs. We evaluate our approach on classification in federated setting, as well as active learning and OOD detection in federated settings, on which our approach outperforms various existing federated learning baselines.

This paper studies the problem of conducting self-supervised learning for node representation learning on graphs. Most existing self-supervised learning methods assume the graph is homophilous, where linked nodes often belong to the same class or have similar features. However, such assumptions of homophily do not always hold in real-world graphs. We address this problem by developing a decoupled self-supervised learning (DSSL) framework for graph neural networks. DSSL imitates a generative process of nodes and links from latent variable modeling of the semantic structure, which decouples different underlying semantics between different neighborhoods into the self-supervised learning process. Our DSSL framework is agnostic to the encoders and does not need prefabricated augmentations, thus is flexible to different graphs. To effectively optimize the framework, we derive the evidence lower bound of the self-supervised objective and develop a scalable training algorithm with variational inference. We provide a theoretical analysis to justify that DSSL enjoys the better downstream performance. Extensive experiments on various types of graph benchmarks demonstrate that our proposed framework can achieve better performance compared with competitive baselines.

How to Do It is Slate's sex advice column. Send it to Stoya and Rich here. My husband and I have an awesome, intelligent 14-year-old son who identifies as bisexual. We are totally accepting and supportive of him. He has had a few short-lived crushes on different genders, though he doesn't seem to be particularly interested in dating right now. His internet search histories are pretty benign--mostly video game stuff, and the occasional search for "hot girls" and "boobs."

Implicit communication plays such a crucial role during social exchanges that it must be considered for a good experience in human-robot interaction. This work addresses implicit communication associated with the detection of physical properties, transport, and manipulation of objects. We propose an ecological approach to infer object characteristics from subtle modulations of the natural kinematics occurring during human object manipulation. Similarly, we take inspiration from human strategies to shape robot movements to be communicative of the object properties while pursuing the action goals. In a realistic HRI scenario, participants handed over cups - filled with water or empty - to a robotic manipulator that sorted them. We implemented an online classifier to differentiate careful/not careful human movements, associated with the cups' content. We compared our proposed "expressive" controller, which modulates the movements according to the cup filling, against a neutral motion controller. Results show that human kinematics is adjusted during the task, as a function of the cup content, even in reach-to-grasp motion. Moreover, the carefulness during the handover of full cups can be reliably inferred online, well before action completion. Finally, although questionnaires did not reveal explicit preferences from participants, the expressive robot condition improved task efficiency.