Search results

In many real-world settings, machine learning models need to identify user inputs that are out-of-domain (OOD) so as to avoid performing wrong actions. This work focuses on a challenging case of OOD detection, where no labels for in-domain data are accessible (e.g., no intent labels for the intent classification task). To this end, we first evaluate different language model based approaches that predict

We consider the task of 3D pose estimation and tracking of multiple people seen in an arbitrary number of camera feeds. We propose TesseTrack1, a novel top-down approach that simultaneously reasons about multiple individuals’ 3D body joint reconstructions and associations in space and time in a single end-to-end learnable framework. At the core of our approach is a novel spatio-temporal formulation that

For supervised learning with tabular data, decision tree ensembles produced via boosting techniques generally dominate real-world applications involving iid training/test sets. However for graph data where the iid assumption is violated due to structured relations between samples, it remains unclear how to best incorporate this structure within existing boosting pipelines. To this end, we propose a generalized

The moiré effect provides an interpretation for the steering of antennas that form beams through internal spatial interferences. We make an explicit connection between such antennas and the moiré effect, and use it to model six planar antennas that steer by scaling, rotating, or translating operations. Three of the antennas illustrate how to use moiré patterns to generate antenna designs.

Training neural machine translation (NMT) models in federated learning (FL) settings could be inefficient both computationally and communication-wise, due to the large size of translation engines as well as the multiple rounds of updates required to train clients and a central server. In this paper, we explore how to efficiently build NMT models in an FL setup by proposing a novel solution. In order to

Neural language models (LM) trained on diverse corpora are known to work well on previously seen entities, however, updating these models with dynamically changing entities such as place names, song titles and shopping items requires re-training from scratch and collecting full sentences containing these entities. We aim to address this issue, by introducing entity-aware language models (EALM), where we

Motivated by modern applications, such as online advertisement and recommender systems, we study the top-k eXtreme contextual bandits problem, where the total number of arms can be enormous, and the learner is allowed to select k arms and observe all or some of the rewards for the chosen arms. We first propose an algorithm for the non-eXtreme realizable setting, utilizing the Inverse Gap Weighting strategy

The paradigm of pre-training followed by finetuning has become a standard procedure for NLP tasks, with a known problem of domain shift between the pre-training and downstream corpus. Previous works have tried to mitigate this problem with additional pre-training, either on the downstream corpus itself when it is large enough, or on a manually curated unlabeled corpus of a similar domain. In this paper,

Calibration means that forecasts and average realized frequencies are close. We develop the concept of forecast hedging, which consists of choosing the forecasts so as to guarantee that the expected track record can only improve. This yields all the calibration results by the same simple basic argument while differentiating between them by the forecast-hedging tools used: deterministic and fixed point based

In online applications with streaming data, awareness of how far the empirical training or test data has shifted away from its original data distribution can be crucial to the performance of the model. However, historical samples in the data stream may not be kept either due to space requirements or for regulatory reasons. To cope with such situations, we propose Continual Density Ratio Estimation (CDRE

Recommending sets of items that include both personalized and compatible items is crucial to personalized styling programs such as Amazon’s Personal Shopper. There is both an extensive literature on learning generic fashion compatibility and also on personalization in fashion. However, recommending pairs of items that the customer would like to wear together is still less studied as it involves learning

We present a privacy preserving machine learning method for images that separates task-relevant information from task-irrelevant information. Our primary hypothesis is that by revealing the minimal number of pixels required for a task we can provide the most privacy preserving guarantees. Specifically, we propose an adversarial method that masks out task-irrelevant information from an image for preserving

Due to intense competition and lack of real estate on the front page of large e-commerce platforms, sellers are sometimes motivated to garner non-genuine signals (clicks, add-to-carts, purchases) on their products, to make them appear more appealing to customers. This hurts customers’ trust on the platform, and also hurts genuine sellers who sell their items without looking to game the system. While it

Batch-mode active learning iteratively selects a batch of unlabeled samples for labelling to maximize model performance and reduce total runtime. To select the most informative and diverse batch, existing methods usually calculate the correlation between samples within a batch, leading to combinatorial optimization problems which are inefficient, complex, and limited to linear models for approximated solutions

Learning-based methods for training embodied agents typically require a large number of high-quality scenes that contain realistic layouts and support meaningful interactions. However, current simulators for Embodied AI (EAI) challenges only provide simulated indoor scenes with a limited number of layouts. This paper presents LUMINOUS, the first research framework that employs stateof-the-art indoor scene

Graph neural networks (GNNs) are a new class of powerful machine learning models, but easy programming and efficient computing is often at odds. Current GNN frameworks are based on a message passing paradigm, and allow the concise expression of GNN models using built-in primitives and user defined functions (UDFs). While built-in primitives offer high performance, they are limited in expressiveness; UDFs

We consider the framework of non-stationary Online Convex Optimization where a learner seeks to control its dynamic regret against an arbitrary sequence of comparators. When the loss functions are strongly convex or exp-concave, we demonstrate that Strongly Adaptive (SA) algorithms can be viewed as a principled way of controlling dynamic regret in terms of path variation VT of the comparator sequence. Specifically

We study the distribution over measurement outcomes of noisy random quantum circuits in the low-fidelity regime. We show that, for local noise that is sufficiently weak and unital, correlations (measured by the linear cross-entropy benchmark) between the output distribution p_(noisy) of a generic noisy circuit instance and the output distribution pideal of the corresponding noiseless instance shrink exponentially

The rise of programmable quantum devices has motivated the exploration of circuit models which could realize novel physics. A promising candidate is a class of hybrid circuits, where entangling unitary dynamics compete with disentangling measurements. Novel phase transitions between different entanglement regimes have been identified in their dynamical states, with universal properties hinting at unexplored

The Eigenstate Thermalization Hypothesis (ETH) has played a major role in explaining thermodynamic phenomena in quantum systems. However, so far, no connection has been known between ETH and the timescale of thermalization. In this paper, we rigorously show that ETH indeed implies fast thermalization to the global Gibbs state. We show fast convergence for two models of thermalization. In the first, the