On Sunday 26.03.23, at 12:00 PM, we will have our third session of students’ presentations. In this session, four students from BIU will present their work. Note that, unlike regular learning club meetings, this meeting will last 2 hours, and will include lunch. It will take place at the Engineering building (1103) in room 329. ... Read more

Title:Efficient Rate Optimal Regret for Adversarial Contextual MDPs Using Online Function ApproximationAbstract:We study learning tabular finite-horizon Markov Decision Processes with adversarially-chosen contexts. Following latest literature, we assume a realizable function class that maps between context and MDP as well as access to online regression oracles that fits the best function given prior observations. This setting ... Read more

Location:Engineering building (1103), room 329Title:When Language Models Meet WordsAbstract:Over the last few years, deep neural models have taken over the field of natural language processing (NLP), brandishing great improvements on many of its sequence-level tasks. But the end-to-end nature of these models makes it hard to figure out whether the way they represent individual words ... Read more

Location:Building 1300 (students’ dorms), room 1Title:What is next in Vision and Language models?Abstract:In recent years, two mostly separated fields of machine learning, computer vision and natural language processing, have gradually become closer. Advancements in each field have greatly influenced the other, driven in part by the abundance of weekly annotated data in the form of ... Read more

Location:Engineering building (1103), room 329Title:Inferring the UnseenAbstract:Consider a finite sample from an unknown distribution over a countable alphabet. Unobserved events are alphabet symbols which do not appear in the sample. Estimating the probabilities of unobserved events is a basic problem in statistics and related fields, which was extensively studied in the context of point estimation. ... Read more

Location:Engineering building (1103), room 329Title:Beyond SGD: Efficient Learning with Non i.i.d. DataAbstract:The tremendous success of the Machine Learning paradigm heavily relies on the development of powerful optimization methods. The canonical algorithm for training learning models is SGD (Stochastic Gradient Descent), yet this method has several limitations. In particular, it relies on the assumption that data-points ... Read more

Location:Engineering building (1103), room 329Title:Improving Graph Neural Networks with Learnable Propagation OperatorsAbstract:Graph Neural Networks (GNNs) are limited in their propagation operators. In many cases, these operators often contain non-negative elements only and are shared across channels, limiting the expressiveness of GNNs. Moreover, some GNNs suffer from over-smoothing, limiting their depth. On the other hand, Convolutional ... Read more

Zoom link: https://biu-ac-il.zoom.us/j/4685913265 Title:Betting as a mechanism to make reliable discoveries Abstract:This talk introduces a new statistical testing framework that allows researchers to analyze an incoming i.i.d. data stream with any arbitrary dependency structure, and safely conclude whether a feature is conditionally associated with the response under study. We allow the processing of data points online, as soon ... Read more

########## TBD##########

########## TBD ##########

########## TBD##########

########## TBD##########

UNFORTUNATELY THIS SESSION IS CANCELED We are Back with BIU AI & ML Learning Club ! On May 5,  Hadar Averbuch-Elor from TAU will give a talk titled : Marrying Vision and Language: A Mutually Beneficial Relationship? Abstract: Foundation models that connect vision and language have recently shown great promise for a wide array of ... Read more

On May 12,  Louis Shekhtman from BIU will give a talk titled: Leveraging Big Data and Network Science to understand Philanthropy Abstract: While philanthropic support has increased in the past decade, there is limited quantitative knowledge about the patterns that characterize it and the mechanisms that drive its distribution. Here, we collected over 3 million ... Read more

On May 19,  Guy Bar-Shalom from the Technion will give a talk titled: Subgraphormer: Unifying Subgraph GNNs and Graph Transformers via Graph Products Abstract: In the realm of Graph Neural Networks (GNNs), two exciting research directions have recently emerged: Subgraph GNNs and Graph Transformers. We propose an architecture that integrates both approaches, dubbed Subgraphormer, which ... Read more

On May 26,  Dr. Or Litany from the Technion will give a talk titled: Real-to-Sim: Towards interpretable and controllable digital twins Abstract: Do we live in a simulation? Perhaps we should consider the possibility. Replicating real-world observations into a digital twin offers numerous potential benefits. For instance, in autonomous navigation, one could recreate safety-critical scenarios ... Read more

On May 26,  Dr. Kfir Levy from the Technion will give a talk titled: Do Stochastic, Feel Noiseless: Stable Optimization via a Double Momentum Mechanism Abstract: The tremendous success of the Machine Learning paradigm heavily relies on the development of powerful optimization methods, and the canonical algorithm for training learning models is SGD (Stochastic Gradient ... Read more

On June 9,  Dr. Wasim Huleihel from the Tel Aviv university will give a talk titled: Testing for Dependency of Databases Abstract: In this talk, we investigate the problem of detecting the dependency between two random databases represented as matrices. This is formalized as a hypothesis testing problem, where under the null hypothesis, the two ... Read more

On June 16,  Dr. Ronen Talmon from the Technion will give a talk titled: Revealing Latent Hierarchical Structures in High-Dimensional Data Using Hyperbolic Representations Abstract: The tremendous success of the Machine Learning paradigm heavily relies on the development of powerful optimization methods, and the canonical algorithm for training learning models is SGD (Stochastic Gradient Descent). ... Read more

On June 23,  we will have 4 BIU Students giving the following talks on their research progress. First hour (12:00-13:00) will be dedicated for the students talks Second hour (13:00 - 14:00) for networking. 12:00 - 12:15 Presenter: Osnat Drien Lab Head: Prof. Yael Amsterdamer Title: Query-Guided Resolution in Uncertain Databases Abstract: We present a ... Read more

On June 30,  Dr. Nadav Cohen from the Tel Aviv University will give a talk titled: What Makes Data Suitable for Deep Learning? Abstract: Deep learning is delivering unprecedented performance when applied to various data modalities, yet there are data distributions over which it utterly fails. The question of what makes a data distribution suitable ... Read more

On July 7,  Prof. Aryeh Kontorovich from the Tel Aviv University will give a talk titled: Local Glivenko-Cantelli (or: estimating the mean in infinite dimensions) Abstract: If μ is a distribution over the d-dimensional Boolean cube {0,1}ᵈ, our goal is to estimate its mean p∈ᵈ based on n iid draws from μ. Specifically, we consider ... Read more

On July 14,  Dr. Adam Hakim from Microsoft WSSI will give a talk titled: Protecting AI From Theft with 2-Party Security Abstract: Large language models (LLMs) have recently seen widespread adoption, in both academia and industry. As these models grow, they become valuable intellectual property (IP), reflecting enormous investments by their owners. Moreover, the high ... Read more

On November 18,  Dr. Haggai Maron from the Technion will give a talk titled: Exploiting Symmetries for Learning in Deep Weight Spaces Abstract: This talk explores the emerging research direction that studies neural network weights as a novel data modality. We'll discuss recent advances in processing and analyzing raw weight matrices, which exhibit inherent symmetries ... Read more

On November 25,  Dr. Nir Weinberger from the Technion will give a talk titled: Statistical curriculum learning -- An elimination algorithm achieving the weak oracle risk Abstract: Curriculum Learning (CL) is a successful machine learning strategy that improves a learner’s performance by ordering the tasks according to difficulty, similarly to the way humans learn.  However, ... Read more