Model-based Reinforcement Learning (MBRL) has been widely adapted due to its sample efficiency. However, existing worst-case regret analysis typically requires optimistic planning, which is not realistic in general. In contrast, motivated by the theory, empirical study utilizes ensemble of models, which achieve state-of-the-art performance on various testing environments. Such deviation between theory and empirical study leads us to question whether randomized model ensemble guarantee optimism, and hence the optimal worst-case regret? This paper partially answers such question from the perspective of reward randomization, a scarcely explored direction of exploration with MBRL. We show that under the kernelized linear regulator (KNR) model, reward randomization guarantees a partial optimism, which further yields a near-optimal worst-case regret in terms of the number of interactions. We further extend our theory to generalized function approximation and identified conditions for reward randomization to attain provably efficient exploration. Correspondingly, we propose concrete examples of efficient reward randomization. To the best of our knowledge, our analysis establishes the first worst-case regret analysis on randomized MBRL with function approximation.

The stochastic proximal point (SPP) methods have gained recent attention for stochastic optimization, with strong convergence guarantees and superior robustness to the classic stochastic gradient descent (SGD) methods showcased at little to no cost of computational overhead added. In this article, we study a minibatch variant of SPP, namely M-SPP, for solving convex composite risk minimization problems. The core contribution is a set of novel excess risk bounds of M-SPP derived through the lens of algorithmic stability theory. Particularly under smoothness and quadratic growth conditions, we show that M-SPP with minibatch-size $n$ and iteration count $T$ enjoys an in-expectation fast rate of convergence consisting of an $\mathcal{O}\left(\frac{1}{T^2}\right)$ bias decaying term and an $\mathcal{O}\left(\frac{1}{nT}\right)$ variance decaying term. In the small-$n$-large-$T$ setting, this result substantially improves the best known results of SPP-type approaches by revealing the impact of noise level of model on convergence rate. In the complementary small-$T$-large-$n$ regime, we provide a two-phase extension of M-SPP to achieve comparable convergence rates. Moreover, we derive a near-tight high probability (over the randomness of data) bound on the parameter estimation error of a sampling-without-replacement variant of M-SPP. Numerical evidences are provided to support our theoretical predictions when substantialized to Lasso and logistic regression models.

After almost four decades in space, a retired NASA satellite is about to fall to earth. The chances of falling satellite debris posing a risk to "anyone on Earth is very low", NASA said in a statement on Saturday. Most of the 2,450kg (5,400lb) satellite will burn up on re-entry but some pieces are expected to survive, according to NASA. The United States space agency put the odds of injury from falling debris at about one-in-9,400. The science satellite is expected to come down on Sunday night at approximately 18:40 EST (23:40 GMT), give or take 17 hours, according to the US defence department.

A key promise of machine learning is the ability to assist users with personal tasks. Because the personal context required to make accurate predictions is often sensitive, we require systems that protect privacy. A gold standard privacy-preserving system will satisfy perfect secrecy, meaning that interactions with the system provably reveal no private information. However, privacy and quality appear to be in tension in existing systems for personal tasks. Neural models typically require copious amounts of training to perform well, while individual users typically hold a limited scale of data, so federated learning (FL) systems propose to learn from the aggregate data of multiple users. FL does not provide perfect secrecy, but rather practitioners apply statistical notions of privacy -- i.e., the probability of learning private information about a user should be reasonably low. The strength of the privacy guarantee is governed by privacy parameters. Numerous privacy attacks have been demonstrated on FL systems and it can be challenging to reason about the appropriate privacy parameters for a privacy-sensitive use case. Therefore our work proposes a simple baseline for FL, which both provides the stronger perfect secrecy guarantee and does not require setting any privacy parameters. We initiate the study of when and where an emerging tool in ML -- the in-context learning abilities of recent pretrained models -- can be an effective baseline alongside FL. We find in-context learning is competitive with strong FL baselines on 6 of 7 popular benchmarks from the privacy literature and a real-world case study, which is disjoint from the pretraining data. We release our code here: https://github.com/simran-arora/focus

From the perspective of any nation, rural areas generally present a comparable set of problems, such as a lack of proper health care, education, living conditions, wages, and market opportunities. Some nations have created and developed the concept of smart villages during the previous few decades, which effectively addresses these issues. The landscape of traditional agriculture has been radically altered by digital agriculture, which has also had a positive economic impact on farmers and those who live in rural regions by ensuring an increase in agricultural production. We explored current issues in rural areas, and the consequences of smart village applications, and then illustrate our concept of smart village from recent examples of how emerging digital agriculture trends contribute to improving agricultural production in this chapter.

In this paper, we study the problem of k-center clustering with outliers. The problem has many important applications in real world, but the presence of outliers can significantly increase the computational complexity. Though a number of methods have been developed in the past decades, it is still quite challenging to design quality guaranteed algorithm with low complexity for this problem. Our idea is inspired by the greedy method, Gonzalez's algorithm, that was developed for solving the ordinary k-center clustering problem. Based on some novel observations, we show that a simple randomized version of this greedy strategy actually can handle outliers efficiently. We further show that this randomized greedy approach also yields small coreset for the problem in doubling metrics (even if the doubling dimension is not given), which can greatly reduce the computational complexity. Moreover, together with the partial clustering framework proposed by Guha et al. (2019), we prove that our coreset method can be applied to distributed data with a low communication complexity. The experimental results suggest that our algorithms can achieve near optimal solutions and yield lower complexities comparing with the existing methods.

$\bf{Purpose}$: To describe the 3D structural changes in both connective and neural tissues of the optic nerve head (ONH) that occur concurrently at different stages of glaucoma using traditional and AI-driven approaches. $\bf{Methods}$: We included 213 normal, 204 mild glaucoma (mean deviation [MD] $\ge$ -6.00 dB), 118 moderate glaucoma (MD of -6.01 to -12.00 dB), and 118 advanced glaucoma patients (MD < -12.00 dB). All subjects had their ONHs imaged in 3D with Spectralis optical coherence tomography. To describe the 3D structural phenotype of glaucoma as a function of severity, we used two different approaches: (1) We extracted human-defined 3D structural parameters of the ONH including retinal nerve fiber layer (RNFL) thickness, lamina cribrosa (LC) shape and depth at different stages of glaucoma; (2) we also employed a geometric deep learning method (i.e. PointNet) to identify the most important 3D structural features that differentiate ONHs from different glaucoma severity groups without any human input. $\bf{Results}$: We observed that the majority of ONH structural changes occurred in the early glaucoma stage, followed by a plateau effect in the later stages. Using PointNet, we also found that 3D ONH structural changes were present in both neural and connective tissues. In both approaches, we observed that structural changes were more prominent in the superior and inferior quadrant of the ONH, particularly in the RNFL, the prelamina, and the LC. As the severity of glaucoma increased, these changes became more diffuse (i.e. widespread), particularly in the LC. $\bf{Conclusions}$: In this study, we were able to uncover complex 3D structural changes of the ONH in both neural and connective tissues as a function of glaucoma severity. We hope to provide new insights into the complex pathophysiology of glaucoma that might help clinicians in their daily clinical care.

Drone advances in Ukraine have accelerated a long-anticipated technology trend that could soon bring the world's first fully autonomous fighting robots to the battlefield, inaugurating a new age of warfare. The longer the war lasts, the more likely it becomes that drones will be used to identify, select and attack targets without help from humans, according to military analysts, combatants and artificial intelligence researchers. That would mark a revolution in military technology as profound as the introduction of the machine gun. Ukraine already has semi-autonomous attack drones and counter-drone weapons endowed with AI. Russia also claims to possess AI weaponry, though the claims are unproven.

We propose the first metric learning system for the recognition of great ape behavioural actions. Our proposed triple stream embedding architecture works on camera trap videos taken directly in the wild and demonstrates that the utilisation of an explicit DensePose-C chimpanzee body part segmentation stream effectively complements traditional RGB appearance and optical flow streams. We evaluate system variants with different feature fusion techniques and long-tail recognition approaches. Results and ablations show performance improvements of ~12% in top-1 accuracy over previous results achieved on the PanAf-500 dataset containing 180,000 manually annotated frames across nine behavioural actions. Furthermore, we provide a qualitative analysis of our findings and augment the metric learning system with long-tail recognition techniques showing that average per class accuracy -- critical in the domain -- can be improved by ~23% compared to the literature on that dataset. Finally, since our embedding spaces are constructed as metric, we provide first data-driven visualisations of the great ape behavioural action spaces revealing emerging geometry and topology. We hope that the work sparks further interest in this vital application area of computer vision for the benefit of endangered great apes.

A level generator is a tool that generates game levels from noise. Training a generator without a dataset suffers from feedback sparsity, since it is unlikely to generate a playable level via random exploration. A common solution is shaped rewards, which guides the generator to achieve subgoals towards level playability, but they consume effort to design and require game-specific domain knowledge. This paper proposes a novel approach to train generators without datasets or shaped rewards by learning at multiple level sizes starting from small sizes and up to the desired sizes. The denser feedback at small sizes negates the need for shaped rewards. Additionally, the generators learn to build levels at various sizes, including sizes they were not trained for. We apply our approach to train recurrent auto-regressive generative flow networks (GFlowNets) for controllable level generation. We also adapt diversity sampling to be compatible with GFlowNets. The results show that our generators create diverse playable levels at various sizes for Sokoban, Zelda, and Danger Dave. When compared with controllable reinforcement learning level generators for Sokoban, the results show that our generators achieve better controllability and competitive diversity, while being 9x faster at training and level generation.