Nash Q-learning may be considered one of the first and most known algorithms in multi-agent reinforcement learning (MARL) for learning policies that constitute a Nash equilibrium of an underlying general-sum Markov game. Its original proof provided asymptotic guarantees and was for the tabular case. Recently, finite-sample guarantees have been provided using more modern RL techniques for the tabular case. Our work analyzes Nash Q-learning using linear function approximation -- a representation regime introduced when the state space is large or continuous -- and provides finite-sample guarantees that indicate its sample efficiency. We find that the obtained performance nearly matches an existing efficient result for single-agent RL under the same representation and has a polynomial gap when compared to the best-known result for the tabular case.

Inverse molecular design is critical in material science and drug discovery, where the generated molecules should satisfy certain desirable properties. In this paper, we propose equivariant energy-guided stochastic differential equations (EEGSDE), a flexible framework for controllable 3D molecule generation under the guidance of an energy function in diffusion models. Formally, we show that EEGSDE naturally exploits the geometric symmetry in 3D molecular conformation, as long as the energy function is invariant to orthogonal transformations. Empirically, under the guidance of designed energy functions, EEGSDE significantly improves the baseline on QM9, in inverse molecular design targeted to quantum properties and molecular structures. Furthermore, EEGSDE is able to generate molecules with multiple target properties by combining the corresponding energy functions linearly.

Fixing energy leakage caused by different anomalies can result in significant energy savings and extended appliance life. Further, it assists grid operators in scheduling their resources to meet the actual needs of end users, while helping end users reduce their energy costs. In this paper, we analyze the patterns pertaining to the power consumption of dishwashers used in two houses of the REFIT dataset. Then two autoencoder (AEs) with 1D-CNN and TCN as backbones are trained to differentiate the normal patterns from the abnormal ones. Our results indicate that TCN outperforms CNN1D in detecting anomalies in energy consumption. Finally, the data from the Fridge_Freezer and the Freezer of house No. 3 in REFIT is also used to evaluate our approach.

The training for deep neural networks (DNNs) demands immense energy consumption, which restricts the development of deep learning as well as increases carbon emissions. Thus, the study of energy-efficient training for DNNs is essential. In training, the linear layers consume the most energy because of the intense use of energy-consuming full-precision (FP32) multiplication in multiply-accumulate (MAC). The energy-efficient works try to decrease the precision of multiplication or replace the multiplication with energy-efficient operations such as addition or bitwise shift, to reduce the energy consumption of FP32 multiplications. However, the existing energy-efficient works cannot replace all of the FP32 multiplications during both forward and backward propagation with low-precision energy-efficient operations. In this work, we propose an Adaptive Layer-wise Scaling PoT Quantization (ALS-POTQ) method and a Multiplication-Free MAC (MF-MAC) to replace all of the FP32 multiplications with the INT4 additions and 1-bit XOR operations. In addition, we propose Weight Bias Correction and Parameterized Ratio Clipping techniques for stable training and improving accuracy. In our training scheme, all of the above methods do not introduce extra multiplications, so we reduce up to 95.8% of the energy consumption in linear layers during training. Experimentally, we achieve an accuracy degradation of less than 1% for CNN models on ImageNet and Transformer model on the WMT En-De task. In summary, we significantly outperform the existing methods for both energy efficiency and accuracy.

In many developing nations, a lack of poverty data prevents critical humanitarian organizations from responding to large-scale crises. Currently, socioeconomic surveys are the only method implemented on a large scale for organizations and researchers to measure and track poverty. However, the inability to collect survey data efficiently and inexpensively leads to significant temporal gaps in poverty data; these gaps severely limit the ability of organizational entities to address poverty at its root cause. We propose a transfer learning model based on surface temperature change and remote sensing data to extract features useful for predicting poverty rates. Machine learning, supported by data sources of poverty indicators, has the potential to estimate poverty rates accurately and within strict time constraints. Higher temperatures, as a result of climate change, have caused numerous agricultural obstacles, socioeconomic issues, and environmental disruptions, trapping families in developing countries in cycles of poverty. To find patterns of poverty relating to temperature that have the highest influence on spatial poverty rates, we use remote sensing data. The two-step transfer model predicts the temperature delta from high resolution satellite imagery and then extracts image features useful for predicting poverty. The resulting model achieved 80% accuracy on temperature prediction. This method takes advantage of abundant satellite and temperature data to measure poverty in a manner comparable to the existing survey methods and exceeds similar models of poverty prediction.

Federated learning is one of the most appealing alternatives to the standard centralized learning paradigm, allowing a heterogeneous set of devices to train a machine learning model without sharing their raw data. However, it requires a central server to coordinate the learning process, thus introducing potential scalability and security issues. In the literature, server-less federated learning approaches like gossip federated learning and blockchain-enabled federated learning have been proposed to mitigate these issues. In this work, we propose a complete overview of these three techniques proposing a comparison according to an integral set of performance indicators, including model accuracy, time complexity, communication overhead, convergence time, and energy consumption. An extensive simulation campaign permits to draw a quantitative analysis considering both feedforward and convolutional neural network models. Results show that gossip federated learning and standard federated solution are able to reach a similar level of accuracy, and their energy consumption is influenced by the machine learning model adopted, the software library, and the hardware used. Differently, blockchain-enabled federated learning represents a viable solution for implementing decentralized learning with a higher level of security, at the cost of an extra energy usage and data sharing. Finally, we identify open issues on the two decentralized federated learning implementations and provide insights on potential extensions and possible research directions in this new research field.

Conventionally, Earth system (e.g., weather and climate) forecasting relies on numerical simulation with complex physical models and hence is both expensive in computation and demanding on domain expertise. With the explosive growth of spatiotemporal Earth observation data in the past decade, data-driven models that apply Deep Learning (DL) are demonstrating impressive potential for various Earth system forecasting tasks. The Transformer as an emerging DL architecture, despite its broad success in other domains, has limited adoption in this area. In this paper, we propose Earthformer, a space-time Transformer for Earth system forecasting. Earthformer is based on a generic, flexible and efficient space-time attention block, named Cuboid Attention. The idea is to decompose the data into cuboids and apply cuboid-level self-attention in parallel. These cuboids are further connected with a collection of global vectors. We conduct experiments on the MovingMNIST dataset and a newly proposed chaotic N-body MNIST dataset to verify the effectiveness of cuboid attention and figure out the best design of Earthformer. Experiments on two real-world benchmarks about precipitation nowcasting and El Niño/Southern Oscillation (ENSO) forecasting show that Earthformer achieves state-of-the-art performance.

Shake tables provide a critical tool for simulating earthquake events and testing the response of structures to seismic forces. However, existing shake tables are either expensive or proprietary. This paper presents the design and implementation of a low-cost, open-source shake table named Shakebot for earthquake engineering research and education, built using Robot Operating System (ROS) and robotic concepts. The Shakebot adapts affordable and high-accuracy components from 3D printers, particularly a closed-loop stepper motor for actuation and a toothed belt for transmission. The stepper motor enables the bed to reach a maximum horizontal acceleration of 11.8 m/s^2 (1.2 g), and velocity of 0.5 m/s, with a 2 kg specimen. The Shakebot is equipped with an accelerometer and a high frame-rate camera for bed motion estimation. The low cost and easy use make the Shakebot accessible to a wide range of users, including students, educators, and researchers in low-resource settings. An important application of the Shakebot is to examine the dynamics of precariously balanced rocks (PBRs), which are negative indicators of earthquakes in nature. Our earlier research built a virtual shake robot in simulation for the PBR study. The Shakebot provides an approach to validate the simulation through physical experiments. The ROS-based perception and motion software facilitates the code transition from our virtual shake robot to the physical Shakebot. The reuse of the control programs ensures that the implemented ground motions are consistent for both the simulation and physical experiments, which is critical to validate our simulation experiments.

Welcome to the wild world of software and carbon emissions, where the digital infrastructure of organizations is a hungry beast, consuming vast amounts of electricity and leaving a trail of greenhouse gas emissions in its wake. The issue is becoming more pronounced as the world accelerates its adoption of artificial intelligence and businesses increasingly rely on software to drive their operations. Picture a data center, a fortress of technology where much of today's software is housed. These sprawling structures gobble up electricity with reckless abandon, with worldwide consumption estimated to be between 220 to 320 terawatt-hours in 2021, according to the International Energy Agency. That's more power than consumed by entire countries such as South Africa, Sweden, or Egypt.

AI has become an integral part of our lives, but its growth in recent years has come at a cost. As AI systems become increasingly complex, their training and usage can generate large amounts of carbon emissions, contributing to global warming and climate change. The relationship between model accuracy and complexity is logarithmic. This means that an exponential increase in model size and training requirements can result in linear improvements to performance. Despite this, less priority is given to developing methods with improved efficiency. We need to be aware of the trade-off between accuracy and efficiency and the model's carbon footprint, both during training and when making inferences.