Achieving statistically significant evaluation with passive sampling of test data is challenging in settings such as extreme classification and record linkage, where significant class imbalance is prevalent. Adaptive importance sampling focuses labeling on informative regions of the instance space, however it breaks data independence assumptions - commonly required for asymptotic guarantees that assure estimates approximate population performance and provide practical confidence intervals. In this paper we develop an adaptive importance sampling framework for supervised evaluation that defines a sequence of proposal distributions given a user-defined discriminative model of p(y|x) and a generalized performance measure to evaluate. Under verifiable conditions on the model and performance measure, we establish strong consistency and a (martingale) central limit theorem for resulting performance estimates. We instantiate our framework with worked examples given stochastic or deterministic label oracle access. Both examples leverage Dirichlet-tree models for practical online evaluation, with the deterministic case achieving asymptotic optimality. Experiments on seven datasets demonstrate an average mean-squared error superior to state-of-the-art samplers on fixed label budgets.

Catastrophic forgetting affects the training of neural networks, limiting their ability to learn multiple tasks sequentially. From the perspective of the well established plasticity-stability dilemma, neural networks tend to be overly plastic, lacking the stability necessary to prevent the forgetting of previous knowledge, which means that as learning progresses, networks tend to forget previously seen tasks. This phenomenon coined in the continual learning literature, has attracted much attention lately, and several families of approaches have been proposed with different degrees of success. However, there has been limited prior work extensively analyzing the impact that different training regimes -- learning rate, batch size, regularization method-- can have on forgetting. In this work, we depart from the typical approach of altering the learning algorithm to improve stability. Instead, we hypothesize that the geometrical properties of the local minima found for each task play an important role in the overall degree of forgetting. In particular, we study the effect of dropout, learning rate decay, and batch size, on forming training regimes that widen the tasks' local minima and consequently, on helping it not to forget catastrophically. Our study provides practical insights to improve stability via simple yet effective techniques that outperform alternative baselines.

Founder and CEO at Fusemachines, an AI Education and AI Talent Solution provider based in NYC. The transition to online learning due to COVID-19 has exposed significant gaps in our school systems. While there have been many technological advancements in the past decade, the education industry has been slower to adapt. Education institutions now have the opportunity to explore the potential of learning supported by artificial intelligence. There are many social and economic factors that shape learning environments.

Online learning, or more specifically, the multi-armed bandit (MAB) problem, focuses on the task of learning the reward distributions from an unknown environment while simultaneously optimizing cumulative rewards over a fixed time horizon T. This problem has been studied extensively when the environment (i.e., reward distributions) is stationary over time, with numerous algorithms proposed to tackle the tradeoff between exploration and exploitation when making decisions (see Bubeck et al. 2012 for a comprehensive review). While the stationarity assumption about the reward distributions greatly simplifies the analysis, it does not hold in many decision problems in OR/MS and other fields when the environment is time-varying. For example, a fashion retailer should take into account the seasonal demand shift when setting the prices for apparels, and a hospital needs to consider the variation of the patient arrival rate when scheduling the medical staff. Despite the practical relevance, it is difficult to develop a learning policy for non-stationary rewards, especially when the dynamics can change arbitrarily over time. Recent studies (Besbes et al., 2015) have considered cases in which the environment does not change fast with respect to the length of the time horizon, e.g., when a budget sublinear in T is imposed on the total variation of the underlying reward distribution.

Real-time video inference on compute-limited edge devices like mobile phones and drones is challenging due to the high computation cost of Deep Neural Network models. In this paper we propose Adaptive Model Streaming (AMS), a cloud-assisted approach to real-time video inference on edge devices. The key idea in AMS is to use online learning to continually adapt a lightweight model running on an edge device to boost its performance on the video scenes in real-time. The model is trained in a cloud server and is periodically sent to the edge device. We discuss the challenges of online learning for video and present a practical design that takes into account the edge device, cloud server, and network bandwidth resource limitations. On the task of video semantic segmentation, our experimental results show 5.1--17.0 percent mean Intersection-over-Union improvement compared to a pre-trained model on several real-world videos. Our prototype can perform video segmentation at 30 frames-per-second with 40 milliseconds camera-to-label latency on a Samsung Galaxy S10+ mobile phone, using less than 400Kbps uplink and downlink bandwidth on the device.

Existing methods for reducing disparate performance of a classifier across different demographic groups assume that one has access to a large data set, thereby focusing on the algorithmic aspect of optimizing overall performance subject to additional constraints. However, poor data collection and imbalanced data sets can severely affect the quality of these methods. In this work, we consider a setting where data collection and optimization are performed simultaneously. In such a scenario, a natural strategy to mitigate the performance difference of the classifier is to provide additional training data drawn from the demographic groups that are worse off. In this paper, we propose to consistently follow this strategy throughout the whole training process and to guide the resulting classifier towards equal performance on the different groups by adaptively sampling each data point from the group that is currently disadvantaged. We provide a rigorous theoretical analysis of our approach in a simplified one-dimensional setting and an extensive experimental evaluation on numerous real-world data sets, including a case study on the data collected during the Flint water crisis.

This research proposes and evaluates scoring and assessment methods for Virtual Reality (VR) training simulators. VR simulators capture detailed n-dimensional human motion data which is useful for performance analysis. Custom made medical haptic VR training simulators were developed and used to record data from 271 trainees of multiple clinical experience levels. DTW Multivariate Prototyping (DTW-MP) is proposed. VR data was classified as Novice, Intermediate or Expert. Accuracy of algorithms applied for time-series classification were: dynamic time warping 1-nearest neighbor (DTW-1NN) 60%, nearest centroid SoftDTW classification 77.5%, Deep Learning: ResNet 85%, FCN 75%, CNN 72.5% and MCDCNN 28.5%. Expert VR data recordings can be used for guidance of novices. Assessment feedback can help trainees to improve skills and consistency. Motion analysis can identify different techniques used by individuals. Mistakes can be detected dynamically in real-time, raising alarms to prevent injuries.

Clustering is a ubiquitous task in data science. Compared to the commonly used $k$-means clustering algorithm, $k$-medoids clustering algorithms require the cluster centers to be actual data points and support arbitrary distance metrics, allowing for greater interpretability and the clustering of structured objects. Current state-of-the-art $k$-medoids clustering algorithms, such as Partitioning Around Medoids (PAM), are iterative and are quadratic in the dataset size $n$ for each iteration, being prohibitively expensive for large datasets. We propose Bandit-PAM, a randomized algorithm inspired by techniques from multi-armed bandits, that significantly improves the computational efficiency of PAM. We theoretically prove that Bandit-PAM reduces the complexity of each PAM iteration from $O(n^2)$ to $O(n \log n)$ and returns the same results with high probability, under assumptions on the data that often hold in practice. We empirically validate our results on several large-scale real-world datasets, including a coding exercise submissions dataset from Code.org, the 10x Genomics 68k PBMC single-cell RNA sequencing dataset, and the MNIST handwritten digits dataset. We observe that Bandit-PAM returns the same results as PAM while performing up to 200x fewer distance computations. The improvements demonstrated by Bandit-PAM enable $k$-medoids clustering on a wide range of applications, including identifying cell types in large-scale single-cell data and providing scalable feedback for students learning computer science online. We also release Python and C++ implementations of our algorithm.

Both uncertainty estimation and interpretability are important factors for trustworthy machine learning systems. However, there is little work at the intersection of these two areas. We address this gap by proposing a novel method for interpreting uncertainty estimates from differentiable probabilistic models, like Bayesian Neural Networks (BNNs). Our method, Counterfactual Latent Uncertainty Explanations (CLUE), indicates how to change an input, while keeping it on the data manifold, such that a BNN becomes more confident about the input's prediction. We validate CLUE through 1) a novel framework for evaluating counterfactual explanations of uncertainty, 2) a series of ablation experiments, and 3) a user study. Our experiments show that CLUE outperforms baselines and enables practitioners to better understand which input patterns are responsible for predictive uncertainty.

A key point in successfully applying deep neural models is the construction of architecture families that contain inductive bias relevant to the application domain. Architectures such as CNNs and RNNs have become the preeminent favorites for modeling images and sequential data, respectively. For example, the inductive bias of CNNs favors locality, as well as translation and scale invariances. With these properties, CNNs work extremely well on image data, and are capable of generating problem-dependent representations that almost completely overcome the need for expert knowledge. Similarly, the inductive bias promoted by RNNs and LSTMs (and more recent models such as transformers) favors both locality and temporal stationarity. When considering tabular data, however, neural networks are not the hypothesis class of choice. Most often, the winning class in learning problems involving tabular data is decision forests. In Kaggle competitions, for example, gradient boosting of decision trees (GBDTs) [6, 9, 19, 14] are generally the superior model. While it is quite practical to use GBDTs for medium size datasets, it is extremely hard to scale these methods to very large datasets (e.g., Google or Facebook scale).