Search results

We propose a memory efficient method, named Stochastic Backpropagation (SBP), for training deep neural networks on videos. It is based on the finding that gradients from incomplete execution for backpropagation can still effectively train the models with minimal accuracy loss, which attributes to the high redundancy of video. SBP keeps all forward paths but randomly and independently removes the backward

We present Syne Tune, a library for large-scale distributed hyperparameter optimization (HPO). Syne Tune’s modular architecture allows users to easily switch between different execution backends to facilitate experimentation and makes it easy to contribute new optimization algorithms. To foster reproducible benchmarking, Syne Tune provides an efficient simulator backend and a benchmarking suite, which are

This repository hosts the REDTab dataset, the largest natural-table relation extraction dataset. In our dataset, we have a total of 9,149 tables, and 22,236 column pairs from Music and Literature domains. We release two categories of REDTab: REDTab-standard: This is the standard REDTab which includes 23 different relations. REDTab-simple: This is a filtered version which only focuses on the top 10 most

Existing approaches for Structure from Motion (SfM) produce impressive 3-D reconstruction results especially when using imagery captured with large parallax. However, to create engaging video-content in movies and TV shows, the amount by which a camera can be moved while filming a particular shot is often limited. The resulting small-motion parallax between video frames makes standard geometry-based SfM

Research Service Workbench (RSW) on AWS is a backend API designed to empower AWS partners to more easily build self-service portals for research institutions, allowing their researchers to create and manage secure research computing environments. RSW builds on AWS services including Amazon S3, Service Catalog, and AWS Systems Manager to deliver comprehensive, cutting-edge capabilities in less time while

Class-incremental learning (CIL) has been widely studied under the setting of starting from a small number of classes (base classes). Instead, we explore an understudied real-world setting of CIL that starts with a strong model pre-trained on a large number of base classes. We hypothesize that a strong base model can provide a good representation for novel classes and incremental learning can be done with

Being able to spot defective parts is a critical component in large-scale industrial manufacturing. A particular challenge that we address in this work is the cold-start problem: fit a model using nominal (non-defective) example images only. While handcrafted solutions per class are possible, the goal is to build systems that work well simultaneously on many different tasks automatically. The best performing

This package contains the Hierarchical Bayesian model to predict sample size for online activity. The bang package (https://cran.rstudio.com/web/packages/bang/index.html) was used and accelerated by modifying it to use sufficient statistics, and to only simulate from the posterior over the hyper-parameters. "misc.R", "beta_prior.R", "binom_beta.R", "hef.R" and "set_and_check_prior.R" are source files from

Quantum Computing Exploration for Drug Discovery on AWS (abbrev. QCEDD), an open-sourced solution customers can launch to design and run computational studies in the area of drug discovery, e.g. molecular docking and protein folding. With this AWS Solution, you can access quantum computers through Amazon Braket. The Amazon Braket Hybrid Job feature allows you to use classical computing and quantum computing

As training deep learning models on large dataset takes a lot of time and resources, it is desired to construct a small synthetic dataset with which we can train deep learning models sufficiently. There are recent works that have explored solutions on condensing image datasets through complex bi-level optimization. For instance, dataset condensation (DC) matches network gradients w.r.t. large-real data

In this paper, we propose a natural notion of individual preference (IP) stability for clustering, which asks that every data point, on average, is closer to the points in its own cluster than to the points in any other cluster. Our notion can be motivated from several perspectives, including game theory and algorithmic fairness. We study several questions related to our proposed notion. We first show that

This repository contains the main codebase for the corresponding NAACL findings paper. In this work, we explored in-domain information storage to adapters by pre-training them on customer reviews via the leave-one-out objective. Further, we fine-tune the pre-trained adapters on a handful of summaries. This method yields state-of-the-art results in terms of ROUGE scores and reduces semantic mistakes in generated

Pre-trained language models have been recently shown to benefit task-oriented dialogue (TOD) systems. Despite their success, existing methods often formulate this task as a cascaded generation problem which can lead to error accumulation across different sub-tasks and greater data annotation overhead. In this study, we present PPTOD, a unified model that seamlessly supports both task-oriented dialogue understanding

We propose FACTGRAPH, a method that decomposes the document and the summary into structured meaning representations (MR), which are more suitable for factuality evaluation. MRs describe core semantic concepts and their relations, aggregating the main content in both document and summary in a canonical form, and reducing data sparsity. FACTGRAPH encodes such graphs using a graph encoder augmented with structure-aware

This repository contains the code for the paper: "Learning dialogue representations from consecutive utterances" (NAACL 2022).

We introduce ReFinED, an efficient end-to-end entity linking model which uses fine-grained entity types and entity descriptions to perform linking. The model performs mention detection, fine-grained entity typing, and entity disambiguation for all mentions within a document in a single forward pass, making it more than 60 times faster than competitive existing approaches. ReFinED also surpasses state-of-the-art

Our dynamic low-rank task-adaptive reparameterization (TARP) and model structure (TAMS) primitives are implemented as a Python library. pip install -e . The initial commit includes this README and the original codebases we build upon, listed below. Later commits isolate our contributions and demonstrate how the library is used, e.g., TARP and TAMS in a meta-learning the difference loop on top of a HuggingFace

This repo is the official implementation of "Earthformer: Exploring space-time transformers for earth system forecasting" that appeared in NeurIPS 2022.

Dialogue meaning representation formulates natural language utterance semantics in their conversational context in an explicit and machine-readable form. Previous work typically follows the intent-slot framework, which is easy for annotation yet limited on scalability for complex linguistic expressions. A line of works alleviates the representation issue by introducing hierarchical structures but challenging

Reliant on too many experiments to learn good actions, current Reinforcement Learning (RL) algorithms have limited applicability in real-world settings, which can be too expensive to allow exploration. We propose an algorithm for batch RL, where effective policies are learned using only a fixed offline dataset instead of online interactions with the environment. The limited data in batch RL produces inherent