Over the last five years, the advanced LIGO and advanced Virgo detectors have completed three observing runs, reporting over 50 gravitational wave sources [3, 4]. Significant improvements in the sensitivity of the advanced LIGO and advanced Virgo detectors during the last three observing runs have increased the observable volume they can probe, thereby increasing the number of gravitational wave observations [4]. As these observatories continue to enhance their detection capabilities, and other detectors join the international array of gravitational wave detectors, it is expected that gravitational wave sources will be observed at a rate of several per day [4, 5]. An ever-increasing catalog of gravitational wave sources will enable systematic studies that will refine and advance our understanding of stellar evolution, cosmology, alternative theories and gravity, among others [6-11]. The combination of gravitational and electromagnetic waves, and cosmic neutrinos, will shed revolutionary insights into the nature of supranuclear matter in neutron stars [12-14] and the formation and evolution of black holes and neutron stars, providing new and detailed information about their astrophysical environments [15-18]. While all of these science goals are feasible in principle given the proven detection capabilities of astronomical observatories, it is equally true that established algorithms for the observation of multi-messenger sources, such as template matching and nearest neighbors, are compute-intensive and poorly scalable [19-23]. Furthermore, available computational resources will remain oversubscribed, and planned enhancements will be rapidly outstripped with the advent of next-generation detectors within the next couple of years [24, 25]. Thus, an urgent rethinking is critical if we are to realize the Multi-Messenger Astrophysics program in the big-data era [26-28]. To contend with these challenges, a number of researchers have been exploring the application of deep learning and GPU-accelerated computing.

Algorithmic fairness has attracted significant attention in recent years, with many quantitative measures suggested for characterizing the fairness of different machine learning algorithms. Despite this interest, the robustness of those fairness measures with respect to an intentional adversarial attack has not been properly addressed. Indeed, most adversarial machine learning has focused on the impact of malicious attacks on the accuracy of the system, without any regard to the system's fairness. We propose new types of data poisoning attacks where an adversary intentionally targets the fairness of a system. Specifically, we propose two families of attacks that target fairness measures. In the anchoring attack, we skew the decision boundary by placing poisoned points near specific target points to bias the outcome. In the influence attack on fairness, we aim to maximize the covariance between the sensitive attributes and the decision outcome and affect the fairness of the model. We conduct extensive experiments that indicate the effectiveness of our proposed attacks.

Problems of cooperation--in which agents seek ways to jointly improve their welfare--are ubiquitous and important. They can be found at scales ranging from our daily routines--such as driving on highways, scheduling meetings, and working collaboratively--to our global challenges--such as peace, commerce, and pandemic preparedness. Arguably, the success of the human species is rooted in our ability to cooperate. Since machines powered by artificial intelligence are playing an ever greater role in our lives, it will be important to equip them with the capabilities necessary to cooperate and to foster cooperation. We see an opportunity for the field of artificial intelligence to explicitly focus effort on this class of problems, which we term Cooperative AI. The objective of this research would be to study the many aspects of the problems of cooperation and to innovate in AI to contribute to solving these problems. Central goals include building machine agents with the capabilities needed for cooperation, building tools to foster cooperation in populations of (machine and/or human) agents, and otherwise conducting AI research for insight relevant to problems of cooperation. This research integrates ongoing work on multi-agent systems, game theory and social choice, human-machine interaction and alignment, natural-language processing, and the construction of social tools and platforms. However, Cooperative AI is not the union of these existing areas, but rather an independent bet about the productivity of specific kinds of conversations that involve these and other areas. We see opportunity to more explicitly focus on the problem of cooperation, to construct unified theory and vocabulary, and to build bridges with adjacent communities working on cooperation, including in the natural, social, and behavioural sciences.

AI systems are often used to make or contribute to important decisions in a growing range of applications, including criminal justice, hiring, and medicine. Since these decisions impact human lives, it is important that the AI systems act in ways which align with human values. Techniques for preference modeling and social choice help researchers learn and aggregate peoples' preferences, which are used to guide AI behavior; thus, it is imperative that these learned preferences are accurate. These techniques often assume that people are willing to express strict preferences over alternatives; which is not true in practice. People are often indecisive, and especially so when their decision has moral implications. The philosophy and psychology literature shows that indecision is a measurable and nuanced behavior -- and that there are several different reasons people are indecisive. This complicates the task of both learning and aggregating preferences, since most of the relevant literature makes restrictive assumptions on the meaning of indecision. We begin to close this gap by formalizing several mathematical \emph{indecision} models based on theories from philosophy, psychology, and economics; these models can be used to describe (indecisive) agent decisions, both when they are allowed to express indecision and when they are not. We test these models using data collected from an online survey where participants choose how to (hypothetically) allocate organs to patients waiting for a transplant.

We study the problem of imposing conversational goals/keywords on open-domain conversational agents, where the agent is required to lead the conversation to a target keyword smoothly and fast. Solving this problem enables the application of conversational agents in many real-world scenarios, e.g., recommendation and psychotherapy. The dominant paradigm for tackling this problem is to 1) train a next-turn keyword classifier, and 2) train a keyword-augmented response retrieval model. However, existing approaches in this paradigm have two limitations: 1) the training and evaluation datasets for next-turn keyword classification are directly extracted from conversations without human annotations, thus, they are noisy and have low correlation with human judgements, and 2) during keyword transition, the agents solely rely on the similarities between word embeddings to move closer to the target keyword, which may not reflect how humans converse. In this paper, we assume that human conversations are grounded on commonsense and propose a keyword-guided neural conversational model that can leverage external commonsense knowledge graphs (CKG) for both keyword transition and response retrieval. Automatic evaluations suggest that commonsense improves the performance of both next-turn keyword prediction and keyword-augmented response retrieval. In addition, both self-play and human evaluations show that our model produces responses with smoother keyword transition and reaches the target keyword faster than competitive baselines.

We consider the problem of online learning in the presence of sudden distribution shifts as frequently encountered in applications such as autonomous navigation. Distribution shifts require constant performance monitoring and re-training. They may also be hard to detect and can lead to a slow but steady degradation in model performance. To address this problem we propose a new Bayesian meta-algorithm that can both (i) make inferences about subtle distribution shifts based on minimal sequential observations and (ii) accordingly adapt a model in an online fashion. The approach uses beam search over multiple change point hypotheses to perform inference on a hierarchical sequential latent variable modeling framework. Our proposed approach is model-agnostic, applicable to both supervised and unsupervised learning, and yields significant improvements over state-of-the-art Bayesian online learning approaches.

Today, India lags behind in the AI race significantly compared to the US or China. Indian university or institutes are not yet top notch AI research entities, either measured by citations or other measures such as winning prestigious AI contests. Most recently, Chinese scientists have demonstrated and claimed "Quantum Supremacy" in a race that seems to upend Google and USA. However, it is not too late, nor is it to India's disadvantage not to have the top-notch algorithm developments taking place outside of the country. The reality is that most useful algorithms make it to the public domain quickly and are widely available.

Netflix has been fairly quiet about Outside the Wire, a sci-fi thriller starring Anthony Mackie from the Marvel Cinematic Universe and Altered Carbon. But today we're getting our first look at the action thanks to a just-released teaser trailer that shows Mackie playing an android super-soldier. The plot details are still fairly fuzzy, but the video's description notes that a "disgraced drone pilot" played by co-star Damson Idris finds himself sent to a dangerous militarized zone where he partners with Mackie to locate a "doomsday device." The cyborg and human then take on huge squads of threatening robots, action ensues. The trailer is mostly focused on hyping up the impressive battle scenes rather than giving much info on how or why things are happening -- but with a month until Outside the Wire arrives on Netflix, it's safe to assume a few more trailers will arrive before then.

Artificial Intelligence (AI) is one of the hottest topics today. Recent advances literally talk for themselves -- say hi to GPT-3, and it will greet you back. AI-discovered pharmaceutics is around the corner. Companies are hiring more Ph. Ds than ever while policy-makers are trying to make sense of this year tech with centuries-old laws.

Getting machine learning and artificial intelligence to work for construction is often a matter of finding where it would be most useful. AI algorithms can scan through terabytes of data, looking for small inconsistencies or hidden patterns that a human might not notice at first. Now, engineers at Thornton Tomasetti have applied that considerable processing power to the tricky work of building-facade inspections. After two years of development in Thornton Tomasetti's CORE lab, the result is T2D2, a computer-vision, machine-learning algorithm that can identify damage to building exteriors in photos or video. Not intended to replace the difficult work of facade inspections, T2D2 is instead seen as tool to find hidden damage that might go unnoticed, and speed along a tedious, difficult process.