Training of large-scale deep neural networks is often constrained by the available computational resources. We study the effect of limited precision data representation and computation on neural network training. Within the context of low-precision fixed-point computations, we observe the rounding scheme to play a crucial role in determining the network's behavior during training. Our results show that deep networks can be trained using only 16-bit wide fixed-point number representation when using stochastic rounding, and incur little to no degradation in the classification accuracy. We also demonstrate an energy-efficient hardware accelerator that implements low-precision fixed-point arithmetic with stochastic rounding.

Applying Machine learning to domains like Earth Sciences is impeded by the lack of labeled data, despite a large corpus of raw data available in such domains. For instance, training a wildfire classifier on satellite imagery requires curating a massive and diverse dataset, which is an expensive and time-consuming process that can span from weeks to months. Searching for relevant examples in over 40 petabytes of unlabelled data requires researchers to manually hunt for such images, much like finding a needle in a haystack. We present a no-code end-to-end pipeline, Curator, which dramatically minimizes the time taken to curate an exhaustive labeled dataset. Curator is able to search massive amounts of unlabelled data by combining self-supervision, scalable nearest neighbor search, and active learning to learn and differentiate image representations. The pipeline can also be readily applied to solve problems across different domains. Overall, the pipeline makes it practical for researchers to go from just one reference image to a comprehensive dataset in a diminutive span of time.

Radiance Fields (RF) are popular to represent casually-captured scenes for new view generation and have been used for applications beyond it. Understanding and manipulating scenes represented as RFs have to naturally follow to facilitate mixed reality on personal spaces. Semantic segmentation of objects in the 3D scene is an important step for that. Prior segmentation efforts using feature distillation show promise but don't scale to complex objects with diverse appearance. We present a framework to interactively segment objects with fine structure. Nearest neighbor feature matching identifies high-confidence regions of the objects using distilled features. Bilateral filtering in a joint spatio-semantic space grows the region to recover accurate segmentation. We show state-of-the-art results of segmenting objects from RFs and compositing them to another scene, changing appearance, etc., moving closer to rich scene manipulation and understanding. Project Page: https://rahul-goel.github.io/isrf/

Stylized view generation of scenes captured casually using a camera has received much attention recently. The geometry and appearance of the scene are typically captured as neural point sets or neural radiance fields in the previous work. An image stylization method is used to stylize the captured appearance by training its network jointly or iteratively with the structure capture network. The state-of-the-art SNeRF method trains the NeRF and stylization network in an alternating manner. These methods have high training time and require joint optimization. In this work, we present StyleTRF, a compact, quick-to-optimize strategy for stylized view generation using TensoRF. The appearance part is fine-tuned using sparse stylized priors of a few views rendered using the TensoRF representation for a few iterations. Our method thus effectively decouples style-adaption from view capture and is much faster than the previous methods. We show state-of-the-art results on several scenes used for this purpose.

Speech-centric machine learning systems have revolutionized many leading domains ranging from transportation and healthcare to education and defense, profoundly changing how people live, work, and interact with each other. However, recent studies have demonstrated that many speech-centric ML systems may need to be considered more trustworthy for broader deployment. Specifically, concerns over privacy breaches, discriminating performance, and vulnerability to adversarial attacks have all been discovered in ML research fields. In order to address the above challenges and risks, a significant number of efforts have been made to ensure these ML systems are trustworthy, especially private, safe, and fair. In this paper, we conduct the first comprehensive survey on speech-centric trustworthy ML topics related to privacy, safety, and fairness. In addition to serving as a summary report for the research community, we point out several promising future research directions to inspire the researchers who wish to explore further in this area.

Chatbots, or bots for short, are multi-modal collaborative assistants that can help people complete useful tasks. Usually, when chatbots are referenced in connection with elections, they often draw negative reactions due to the fear of mis-information and hacking. Instead, in this paper, we explore how chatbots may be used to promote voter participation in vulnerable segments of society like senior citizens and first-time voters. In particular, we build a system that amplifies official information while personalizing it to users' unique needs transparently. We discuss its design, build prototypes with frequently asked questions (FAQ) election information for two US states that are low on an ease-of-voting scale, and report on its initial evaluation in a focus group. Our approach can be a win-win for voters, election agencies trying to fulfill their mandate and democracy at large.

We study the task of training regression models with the guarantee of label differential privacy (DP). Based on a global prior distribution on label values, which could be obtained privately, we derive a label DP randomization mechanism that is optimal under a given regression loss function. We prove that the optimal mechanism takes the form of a ``randomized response on bins'', and propose an efficient algorithm for finding the optimal bin values. We carry out a thorough experimental evaluation on several datasets demonstrating the efficacy of our algorithm.

This paper presents a state-of-the-art optimal controller for quadruped locomotion. The robot dynamics is represented using a single rigid body (SRB) model. A linear time-varying model predictive controller (LTV MPC) is proposed by using linearization schemes. Simulation results show that the LTV MPC can execute various gaits, such as trot and crawl, and is capable of tracking desired reference trajectories even under unknown external disturbances. The LTV MPC is implemented as a quadratic program using qpOASES through the CasADi interface at 50 Hz. The proposed MPC can reach up to 1 m/s top speed with an acceleration of 0.5 m/s2 executing a trot gait. The implementation is available at https:// github.com/AndrewZheng-1011/Quad_ConvexMPC

We study the relationship between adversarial robustness and differential privacy in high-dimensional algorithmic statistics. We give the first black-box reduction from privacy to robustness which can produce private estimators with optimal tradeoffs among sample complexity, accuracy, and privacy for a wide range of fundamental high-dimensional parameter estimation problems, including mean and covariance estimation. We show that this reduction can be implemented in polynomial time in some important special cases. In particular, using nearly-optimal polynomial-time robust estimators for the mean and covariance of high-dimensional Gaussians which are based on the Sum-of-Squares method, we design the first polynomial-time private estimators for these problems with nearly-optimal samples-accuracy-privacy tradeoffs. Our algorithms are also robust to a constant fraction of adversarially-corrupted samples.

Active speaker detection in videos addresses associating a source face, visible in the video frames, with the underlying speech in the audio modality. The two primary sources of information to derive such a speech-face relationship are i) visual activity and its interaction with the speech signal and ii) co-occurrences of speakers' identities across modalities in the form of face and speech. The two approaches have their limitations: the audio-visual activity models get confused with other frequently occurring vocal activities, such as laughing and chewing, while the speakers' identity-based methods are limited to videos having enough disambiguating information to establish a speech-face association. Since the two approaches are independent, we investigate their complementary nature in this work. We propose a novel unsupervised framework to guide the speakers' cross-modal identity association with the audio-visual activity for active speaker detection. Through experiments on entertainment media videos from two benchmark datasets, the AVA active speaker (movies) and Visual Person Clustering Dataset (TV shows), we show that a simple late fusion of the two approaches enhances the active speaker detection performance.