Search results

Per-example gradient clipping is a key algorithmic step that enables practical differential private (DP) training for deep learning models. The choice of clipping threshold R, however, is vital for achieving high accuracy under DP. We propose an easy-to-use replacement, called automatic clipping, that eliminates the need to tune R for any DP optimizers, including DP-SGD, DP-Adam, DP-LAMB and many others

We present a comprehensive architectural analysis for a proposed fault-tolerant quantum computer based on cat codes concatenated with outer quantum error-correcting codes. For the physical hardware, we propose a system of acoustic resonators coupled to superconducting circuits with a two-dimensional layout. Using estimated physical parameters for the hardware, we perform a detailed error analysis of measurements

We simulate, using nonperturbative methods, the real-time dynamics of small bubbles of “false vacuum” in a quantum spin chain near criticality, where the low-energy physics is described by a relativistic (1+1)-dimensional quantum field theory. We consider bubbles whose walls are kink and antikink quasiparticle excitations, so that wall collisions are kink-antikink scattering events. To construct these bubbles

We study the dynamical properties of the bosonic quantum East model at low temperature. We show that a naive generalization of the corresponding spin-1/2 quantum East model does not possess analogous slow dynamical properties. In particular, conversely to the spin case, the bosonic ground state turns out to be not localized. We restore localization by introducing a repulsive interaction term. The bosonic

We introduce a morphing procedure that can be used to generate new quantum codes from existing quantum codes. In particular, we morph the 15-qubit Reed-Muller code to obtain a [[10,1,2]] code that is the smallest-known stabilizer code with a fault-tolerant logical T gate. In addition, we construct a family of hybrid color-toric codes by morphing the color code. Our code family inherits the fault-tolerant

We consider quantum circuits consisting of randomly chosen two-local gates and study the number of gates needed for the distribution over measurement outcomes for typical circuit instances to be anticoncentrated, roughly meaning that the probability mass is not too concentrated on a small number of measurement outcomes. An understanding of the conditions for anticoncentration is important for determining

We consider quantum error-correcting subsystem codes whose gauge generators realize a translation-invariant, free-fermion-solvable spin model. In this setting, errors are suppressed by a Hamiltonian whose terms are the gauge generators of the code and whose exact spectrum and eigenstates can be found via a generalized Jordan-Wigner transformation. Such solutions are characterized by the frustration graph

Realizing quantum speedup for practically relevant, computationally hard problems is a central challenge in quantum information science. Using Rydberg atom arrays with up to 289 qubits in two spatial dimensions, we experimentally investigate quantum algorithms for solving the maximum independent set problem. We use a hardware-efficient encoding associated with Rydberg blockade, realize closed-loop optimization

Understanding human language often necessitates understanding entities and their place in a taxonomy of knowledge—their types. Previous methods to learn entity types rely on training classifiers on datasets with coarse, noisy, and incomplete labels. We introduce a method to instill fine-grained type knowledge in language models with text-to-text pre-training on type-centric questions leveraging knowledge

We present MaCLR, a novel method to explicitly perform cross-modal self-supervised video representations learning from visual and motion modalities. Compared to previous video representation learning methods that mostly focus on learning motion cues implicitly from RGB inputs, MaCLR enriches standard contrastive learning objectives for RGB video clips with a cross-modal learning objective between a Motion

This is the official CERBERUS model code repository for our long paper in Findings of EMNLP 2022, "Ensemble Transformer for Efficient and Accurate Ranking Tasks: an Application to Question Answering Systems".

This paper presents a new large scale multi-person tracking dataset – PersonPath22, which is over an order of magnitude larger than currently available high quality multi-object tracking datasets such as MOT17, HiEve, and MOT20 datasets. The lack of large scale training and test data for this task has limited the community’s ability to understand the performance of their tracking systems on a wide range

We propose TubeR: a simple solution for spatio-temporal video action detection. Different from existing methods that depend on either an off-line actor detector or hand-designed actor-positional hypotheses like proposals or anchors, we propose to directly detect an action tubelet in a video by simultaneously performing action localization and recognition from a single representation. TubeR learns a set

Large-scale pre-trained sequence-to-sequence models like BART and T5 achieve state-of-the-art performance on many generative NLP tasks. However, such models pose a great challenge in resource-constrained scenarios owing to their large memory requirements and high latency. To alleviate this issue, we propose to jointly distill and quantize the model, where knowledge is transferred from the full-precision

The package defines a set of tool to access the annotated data we collected for 2022 Amazon Alexa language-assisted product search challenge.

Data augmentation is a necessity to enhance data efficiency in deep learning. For vision-language pre-training, data is only augmented either for images or for text in previous works. In this paper, we present MixGen: a joint data augmentation for vision-language representation learning to further improve data efficiency. It generates new image-text pairs with semantic relationships preserved by interpolating

Recent years have witnessed an emerging paradigm shift toward embodied artificial intelligence, in which an agent must learn to solve challenging tasks by interacting with its environment. There are several challenges in solving embodied multimodal tasks, including long-horizon planning, vision-and-language grounding, and efficient exploration. We focus on a critical bottleneck, namely the performance of

This repository contains the files for the blogpost "Detect adversarial inputs using Amazon SageMaker Model Monitor and Amazon SageMaker Debugger". Create a SageMaker notebook instance and clone the repository: git clone https://github.com/amazon-research/detecting-adversarial-samples-using-sagemaker.git In the notebook Detecting_adversarial_samples.ipynb we first train an image classification model (ResNet18

We introduce MINTAKA, a complex, natural, and multilingual dataset designed for experimenting with end-to-end question-answering models. Mintaka is composed of 20,000 question-answer pairs collected in English, annotated with Wikidata entities, and translated into Arabic, French, German, Hindi, Italian, Japanese, Portuguese, and Spanish for a total of 180,000 samples. Mintaka includes 8 types of complex

An open-licensed dataset of Amazon products with metadata, catalog images, and artist-created 3D models with complex geometries and physically-based materials that correspond to real, household objects. The unique properties of ABO allow to benchmark the state of the art on several open problems for real-world 3D object understanding: single-view 3D reconstruction, fine-grained part labelling, material