Mirror descent, introduced by Nemirovski and Yudin in the 1970s, is a primal-dual convex optimization method that can be tailored to the geometry of the optimization problem at hand through the choice of a strongly convex potential function. It arises as a basic primitive in a variety of applications, including large-scale optimization, machine learning, and control. This paper proposes a variational formulation of mirror descent and of its stochastic variant, mirror Langevin dynamics. The main idea, inspired by the classic work of Brezis and Ekeland on variational principles for gradient flows, is to show that mirror descent emerges as a closed-loop solution for a certain optimal control problem, and the Bellman value function is given by the Bregman divergence between the initial condition and the global minimizer of the objective function.

Reproduced under a CC BY 3.0 licence. How does an iPhone predict the next word you're going to type in your messages? The technology behind this, and also at the core of many AI applications, is called a transformer; a deep-learning model that handles sequences of data in parallel, and can be fine-tuned for specific tasks. Now, researchers at EPFL and KAIST have created a transformer for Metal-Organic Frameworks (MOFs), a class of porous crystalline materials whose potential applications include energy storage and gas separation. MOFs are composed of thousands of tunable molecular building blocks (metal nodes and organic linkers), and, considering all possible configurations, a vast number of MOFs could potentially be synthesised.

With its uncanny ability to hold a conversation, answer questions, and write coherent prose, poetry, and code, the chatbot ChatGPT has forced many people to rethink the potential of artificial intelligence. The startup that made ChatGPT, OpenAI, today announced a much-anticipated new version of the AI model at its core. The new algorithm, called GPT-4, follows GPT-3, a groundbreaking text-generation model that OpenAI announced in 2020, which was later adapted to create ChatGPT last year. The new model scores more highly on a range of tests designed to measure intelligence and knowledge in humans and machines, OpenAI says. It also makes fewer blunders and can respond to images as well as text.

To avoid a bottleneck of bots, a team of MIT engineers is designing a kit of universal robotic parts that an astronaut could easily mix and match to rapidly configure different robot "species" to fit various missions on the moon. Once a mission is completed, a robot can be disassembled and its parts used to configure a new robot to meet a different task. The team calls the system WORMS, for the Walking Oligomeric Robotic Mobility System. The system's parts include worm-inspired robotic limbs that an astronaut can easily snap onto a base, and that work together as a walking robot. Depending on the mission, parts can be configured to build, for instance, large "pack" bots capable of carrying heavy solar panels up a hill.

With the rapid advancement of Intelligent Transportation Systems (ITS) and vehicular communications, Vehicular Edge Computing (VEC) is emerging as a promising technology to support low-latency ITS applications and services. In this paper, we consider the computation offloading problem from mobile vehicles/users in a heterogeneous VEC scenario, and focus on the network- and base station selection problems, where different networks have different traffic loads. In a fast-varying vehicular environment, computation offloading experience of users is strongly affected by the latency due to the congestion at the edge computing servers co-located with the base stations. However, as a result of the non-stationary property of such an environment and also information shortage, predicting this congestion is an involved task. To address this challenge, we propose an on-line learning algorithm and an off-policy learning algorithm based on multi-armed bandit theory. To dynamically select the least congested network in a piece-wise stationary environment, these algorithms predict the latency that the offloaded tasks experience using the offloading history. In addition, to minimize the task loss due to the mobility of the vehicles, we develop a method for base station selection. Moreover, we propose a relaying mechanism for the selected network, which operates based on the sojourn time of the vehicles. Through intensive numerical analysis, we demonstrate that the proposed learning-based solutions adapt to the traffic changes of the network by selecting the least congested network, thereby reducing the latency of offloaded tasks. Moreover, we demonstrate that the proposed joint base station selection and the relaying mechanism minimize the task loss in a vehicular environment.

We present Gradient Gating (G$^2$), a novel framework for improving the performance of Graph Neural Networks (GNNs). Our framework is based on gating the output of GNN layers with a mechanism for multi-rate flow of message passing information across nodes of the underlying graph. Local gradients are harnessed to further modulate message passing updates. Our framework flexibly allows one to use any basic GNN layer as a wrapper around which the multi-rate gradient gating mechanism is built. We rigorously prove that G$^2$ alleviates the oversmoothing problem and allows the design of deep GNNs. Empirical results are presented to demonstrate that the proposed framework achieves state-of-the-art performance on a variety of graph learning tasks, including on large-scale heterophilic graphs.

The working mechanisms of complex natural systems tend to abide by concise and profound partial differential equations (PDEs). Methods that directly mine equations from data are called PDE discovery, which reveals consistent physical laws and facilitates our adaptive interaction with the natural world. In this paper, an enhanced deep reinforcement-learning framework is proposed to uncover symbolically concise open-form PDEs with little prior knowledge. Particularly, based on a symbol library of basic operators and operands, a structure-aware recurrent neural network agent is designed and seamlessly combined with the sparse regression method to generate concise and open-form PDE expressions. All of the generated PDEs are evaluated by a meticulously designed reward function by balancing fitness to data and parsimony, and updated by the model-based reinforcement learning in an efficient way. Customized constraints and regulations are formulated to guarantee the rationality of PDEs in terms of physics and mathematics. The experiments demonstrate that our framework is capable of mining open-form governing equations of several dynamic systems, even with compound equation terms, fractional structure, and high-order derivatives, with excellent efficiency. Without the need for prior knowledge, this method shows great potential for knowledge discovery in more complicated circumstances with exceptional efficiency and scalability.

The paper proposes a new algorithm called SymBa that aims to achieve more biologically plausible learning than Back-Propagation (BP). The algorithm is based on the Forward-Forward (FF) algorithm, which is a BP-free method for training neural networks. SymBa improves the FF algorithm's convergence behavior by addressing the problem of asymmetric gradients caused by conflicting converging directions for positive and negative samples. The algorithm balances positive and negative losses to enhance performance and convergence speed. Furthermore, it modifies the FF algorithm by adding Intrinsic Class Pattern (ICP) containing class information to prevent the loss of class information during training. The proposed algorithm has the potential to improve our understanding of how the brain learns and processes information and to develop more effective and efficient artificial intelligence systems. The paper presents experimental results that demonstrate the effectiveness of SymBa algorithm compared to the FF algorithm and BP.

The paper introduces an interactive machine learning mechanism to process the measurements of an uncertain, nonlinear dynamic process and hence advise an actuation strategy in real-time. For concept demonstration, a trajectory-following optimization problem of a Kinova robotic arm is solved using an integral reinforcement learning approach with guaranteed stability for slowly varying dynamics. The solution is implemented using a model-free value iteration process to solve the integral temporal difference equations of the problem. The performance of the proposed technique is benchmarked against that of another model-free high-order approach and is validated for dynamic payload and disturbances. Unlike its benchmark, the proposed adaptive strategy is capable of handling extreme process variations. This is experimentally demonstrated by introducing static and time-varying payloads close to the rated maximum payload capacity of the manipulator arm. The comparison algorithm exhibited up to a seven-fold percent overshoot compared to the proposed integral reinforcement learning solution. The robustness of the algorithm is further validated by disturbing the real-time adapted strategy gains with a white noise of a standard deviation as high as 5%.

Mathematical models for the generation of the action potential can improve the understanding of physiological mechanisms that are consequence of the electrical activity in neurons. In such models, some equations involving empirically obtained functions of the membrane potential are usually defined. The best known of these models, the Hodgkin-Huxley model, is an example of this paradigm since it defines the conductances of ion channels in terms of the opening and closing rates of each type of gate present in the channels. These functions need to be derived from laboratory measurements that are often very expensive and produce little data because they involve a time-space-independent measurement of the voltage in a single channel of the cell membrane. In this work, we investigate the possibility of finding the Hodgkin-Huxley model's parametric functions using only two simple measurements (the membrane voltage as a function of time and the injected current that triggered that voltage) and applying Deep Learning methods to estimate these functions. This would result in an hybrid model of the action potential generation composed by the original Hodgkin-Huxley equations and an Artificial Neural Network that requires a small set of easy-to-perform measurements to be trained. Experiments were carried out using data generated from the original Hodgkin-Huxley model, and results show that a simple two-layer artificial neural network (ANN) architecture trained on a minimal amount of data can learn to model some of the fundamental proprieties of the action potential generation by estimating the model's rate functions.