We use cookies to analyze the browsing and usage of our website and to personalize your experience. You can disable these technologies at any time, but this may limit certain functionalities of the site. Read our Privacy Policy for more information.
Setting cookies
You can enable and disable the types of cookies you wish to accept. However certain choices you make could affect the services offered on our sites (e.g. suggestions, personalised ads, etc.).
Essential cookies
These cookies are necessary for the operation of the site and cannot be deactivated. (Still active)
Analytics cookies
Do you accept the use of cookies to measure the audience of our sites?
Multimedia Player
Do you accept the use of cookies to display and allow you to watch the video content hosted by our partners (YouTube, etc.)?
Publications
Mean-field approximation for large-population beauty-contest games
We study a class of Keynesian beauty contest games where a large number of heterogeneous players attempt to estimate a common parameter base… (see more)d on their own observations. The players are rewarded for producing an estimate close to a certain multiplicative factor of the average decision, this factor being specific to each player. This model is motivated by scenarios arising in commodity or financial markets, where investment decisions are sometimes partly based on following a trend. We provide a method to compute Nash equilibria within the class of affine strategies. We then develop a mean-field approximation, in the limit of an infinite number of players, which has the advantage that computing the best-response strategies only requires the knowledge of the parameter distribution of the players, rather than their actual parameters. We show that the mean-field strategies lead to an ε-Nash equilibrium for a system with a finite number of players. We conclude by analyzing the impact on individual behavior of changes in aggregate population behavior.
2021-12-14
IEEE Conference on Decision and Control (published)
We consider optimal control of an unknown multi-agent linear quadratic (LQ) system where the dynamics and the cost are coupled across the ag… (see more)ents through the mean-field (i.e., empirical mean) of the states and controls. Directly using single-agent LQ learning algorithms in such models results in regret which increases polynomially with the number of agents. We propose a new Thompson sampling based learning algorithm which exploits the structure of the system model and show that the expected Bayesian regret of our proposed algorithm for a system with agents of |M| different types at time horizon T is
2021-12-14
2021 60th IEEE Conference on Decision and Control (CDC) (published)
Adoption of recently developed methods from machine learning has given rise to creation of drug-discovery knowledge graphs (KGs) that utiliz… (see more)e the interconnected nature of the domain. Graph-based modelling of the data, combined with KG embedding (KGE) methods, are promising as they provide a more intuitive representation and are suitable for inference tasks such as predicting missing links. One common application is to produce ranked lists of genes for a given disease, where the rank is based on the perceived likelihood of association between the gene and the disease. It is thus critical that these predictions are not only pertinent but also biologically meaningful. However, KGs can be biased either directly due to the underlying data sources that are integrated or due to modelling choices in the construction of the graph, one consequence of which is that certain entities can get topologically overrepresented. We demonstrate the effect of these inherent structural imbalances, resulting in densely connected entities being highly ranked no matter the context. We provide support for this observation across different datasets, models as well as predictive tasks. Further, we present various graph perturbation experiments which yield more support to the observation that KGE models can be more influenced by the frequency of entities rather than any biological information encoded within the relations. Our results highlight the importance of data modelling choices, and emphasizes the need for practitioners to be mindful of these issues when interpreting model outputs and during KG composition.
Arti fi cial intelligence (AI) based devices are currently being used in the delivery of surgical care in a variety of settings. 1,2 Howeve… (see more)r, AI-enabled systems can trigger a variety of opinions and emotions, which reveals the different lenses that shape views on AI. Nonethless, work within surgical education may necessitate a more balanced view; with an acknowledgment of the participation of AI-enhanced devices in the delivery of surgical care and education
Few-shot learning aims to learn representations that can tackle novel tasks given a small number of examples. Recent studies show that task … (see more)distribution plays a vital role in the performance of the model. Conventional wisdom is that task diversity should improve the performance of meta-learning. In this work, we find evidence to the contrary; we study different task distributions on a myriad of models and datasets to evaluate the effect of task diversity on meta-learning algorithms. For this experiment, we train on two datasets - Omniglot and miniImageNet and with three broad classes of meta-learning models - Metric-based (i.e., Protonet, Matching Networks), Optimization-based (i.e., MAML, Reptile, and MetaOptNet), and Bayesian meta-learning models (i.e., CNAPs). Our experiments demonstrate that the effect of task diversity on all these algorithms follows a similar trend, and task diversity does not seem to offer any benefits to the learning of the model. Furthermore, we also demonstrate that even a handful of tasks, repeated over multiple batches, would be sufficient to achieve a performance similar to uniform sampling and draws into question the need for additional tasks to create better models.
Recent generative models such as generative adversarial networks have achieved remarkable success in generating realistic images, but they r… (see more)equire large training datasets and computational resources. The goal of few-shot image generation is to learn the distribution of a new dataset from only a handful of examples by transferring knowledge learned from structurally similar datasets. Towards achieving this goal, we propose the “Implicit Support Set Autoencoder” (ISSA) that adversarially learns the relationship across datasets using an unsupervised dataset representation, while the distribution of each individual dataset is learned using implicit distributions. Given a few examples from a new dataset, ISSA can generate new samples by inferring the representation of the underlying distribution using a single forward pass. We showcase significant gains from our method on generating high quality and diverse images for unseen classes in the Omniglot and CelebA datasets in few-shot image generation settings.
Significance The uptake of molecules into cells, known as endocytosis, requires membrane invagination and the formation of vesicles. A versi… (see more)on of endocytosis that is independent of actin polymerization is aided by the assembly of membraneless biomolecular condensates at the site of membrane invagination. Here, we show that endocytic condensates are viscoelastic bodies that concentrate key proteins with prion-like domains to enable membrane remodeling. A distinct molecular grammar, namely the preference for glutamine versus asparagine residues, underlies the cohesive interactions that give rise to endocytic condensates. We incorporate material properties inferred using active rheology into a mechanical model to explain how cohesive interactions within condensates and interfacial tensions among condensates, membranes, and the cytosol can drive membrane invagination to initiate endocyosis. Membrane invagination and vesicle formation are key steps in endocytosis and cellular trafficking. Here, we show that endocytic coat proteins with prion-like domains (PLDs) form hemispherical puncta in the budding yeast, Saccharomyces cerevisiae. These puncta have the hallmarks of biomolecular condensates and organize proteins at the membrane for actin-dependent endocytosis. They also enable membrane remodeling to drive actin-independent endocytosis. The puncta, which we refer to as endocytic condensates, form and dissolve reversibly in response to changes in temperature and solution conditions. We find that endocytic condensates are organized around dynamic protein–protein interaction networks, which involve interactions among PLDs with high glutamine contents. The endocytic coat protein Sla1 is at the hub of the protein–protein interaction network. Using active rheology, we inferred the material properties of endocytic condensates. These experiments show that endocytic condensates are akin to viscoelastic materials. We use these characterizations to estimate the interfacial tension between endocytic condensates and their surroundings. We then adapt the physics of contact mechanics, specifically modifications of Hertz theory, to develop a quantitative framework for describing how interfacial tensions among condensates, the membrane, and the cytosol can deform the plasma membrane to enable actin-independent endocytosis.
2021-12-09
Proceedings of the National Academy of Sciences of the United States of America (published)
