Papers

  • Riemannian Metric Learning via Optimal Transport

    We introduce an optimal transport-based model for learning a metric tensor from cross-sectional samples of evolving probability measures on a common Riemannian manifold. We neurally parametrize the metric as a spatially-varying matrix field and efficiently optimize our model's objective using backpropagation. Using this learned metric, we can nonlinearly interpolate between …

  • On Efficiently Partitioning a Topic in Apache Kafka

    Apache Kafka addresses the general problem of delivering extreme high volume event data to diverse consumers via a publish-subscribe messaging system. It uses partitions to scale a topic across many brokers for producers to write data in parallel, and also to facilitate parallel reading of consumers. Even though Apache Kafka …

  • Neural network topological snake models for locating general phase diagrams

    Machine learning for locating phase diagram has received intensive research interest in recent years. However, its application in automatically locating phase diagram is limited to single closed phase boundary. In this paper, in order to locate phase diagrams with multiple phases and complex boundaries, we introduce (i) a network-shaped snake …

  • Two-Step Question Retrieval for Open-Domain QA

    The retriever-reader pipeline has shown promising performance in open-domain QA but suffers from a very slow inference speed. Recently proposed question retrieval models tackle this problem by indexing question-answer pairs and searching for similar questions. These models have shown a significant increase in inference speed, but at the cost of …

  • Spherical Perspective on Learning with Normalization Layers

    Normalization Layers (NLs) are widely used in modern deep-learning architectures. Despite their apparent simplicity, their effect on optimization is not yet fully understood. This paper introduces a spherical framework to study the optimization of neural networks with NLs from a geometric perspective. Concretely, the radial invariance of groups of parameters, …

  • Sum-Rate Optimal Relay Selection and Power Control in Multi-Hop Networks

    In this paper, we focus on the achievable sum-rate optimization problem of a multi-user, multi-hop relay network. We analyze the joint relay selection and power control in the presence of interference such that the achievable sum-rate is maximized. First, we evaluate the achievable sum-rate under five relay selection strategies when …

  • HandoverSim: A Simulation Framework and Benchmark for Human-to-Robot Object Handovers

    We introduce a new simulation benchmark "HandoverSim" for human-to-robot object handovers. To simulate the giver's motion, we leverage a recent motion capture dataset of hand grasping of objects. We create training and evaluation environments for the receiver with standardized protocols and metrics. We analyze the performance of a set of …

  • Consistent Interpolating Ensembles via the Manifold-Hilbert Kernel

    Recent research in the theory of overparametrized learning has sought to establish generalization guarantees in the interpolating regime. Such results have been established for a few common classes of methods, but so far not for ensemble methods. We devise an ensemble classification method that simultaneously interpolates the training data, and …

  • The Quantum Internet: Enhancing Classical Internet Services one Qubit at a Time

    Nowadays, the classical Internet has mainly envisioned as the underlying communication infrastructure of the Quantum Internet, aimed at providing services such as signaling and coordination messages. However, the interplay between classical and Quantum Internet is complex and its understanding is pivotal for an effective design of the Quantum Internet protocol …