arXiv subjects

Yucheng Yang

Publications and source records attributed to Yucheng Yang.

29 records · Page 2Linked to original sources

arXiv2025

Task Adaptation from Skills: Information Geometry, Disentanglement, and New Objectives for Unsupervised Reinforcement Learning

Unsupervised reinforcement learning (URL) aims to learn general skills for unseen downstream tasks. Mutual Information Skill Learning (MISL) addresses URL by maximizing the mutual information between states and skills but lacks sufficient theoretical analysis, e.g., how well its learned skills can initialize a downstream task's policy. Our new theoretical analysis in this paper shows that the diversity and separability of learned skills are fundamentally critical to downstream task adaptation but MISL does not necessarily guarantee these properties. To complement MISL, we propose a novel disentanglement metric LSEPIN. Moreover, we build an information-geometric connection between LSEPIN and downstream task adaptation cost. For better geometric properties, we investigate a new strategy that replaces the KL divergence in information geometry with Wasserstein distance. We extend the geometric analysis to it, which leads to a novel skill-learning objective WSEP. It is theoretically justified to be helpful to downstream task adaptation and it is capable of discovering more initial policies for downstream tasks than MISL. We finally propose another Wasserstein distance-based algorithm PWSEP that can theoretically discover all optimal initial policies.

cs.LG↗

arXiv2024

Evaluating the Impact of Warning Modalities and False Alarms in Pedestrian Crossing Alert System

With the steadily increasing pedestrian fatalities, pedestrian safety is a growing concern, especially in urban environments. Advanced Driver Assistance Systems (ADAS) have been developed to mitigate road user risks by predicting potential pedestrian crossings and issuing timely driver alerts. However, there is limited understanding of how drivers respond to different modalities of alerts, particularly in the presence of false alarms. In this study, we utilized a full-scale driving simulator to compare the effectiveness of different alert modalities, audio-visual (AV), visual-tactile (VT), and audio-visual-tactile (AVT), in alerting drivers to various pedestrian jaywalking events. Our findings reveal that, compared to no alerts, multimodal alerts significantly increased the number of vehicles stopped for pedestrians and the distance to pedestrians when stopped. However, the false alarms negatively impacted driver trust, with some drivers exhibiting excessive caution, alert fatigue and anxiety, even including one instance where a driver fully stopped when no pedestrian was present.

cs.HC↗

arXiv2024

Reliable Heading Tracking for Pedestrian Road Crossing Prediction Using Commodity Devices

Pedestrian heading tracking enables applications in pedestrian navigation, traffic safety, and accessibility. Previous works, using inertial sensor fusion or machine learning, are limited in that they assume the phone is fixed in specific orientations, hindering their generalizability. We propose a new heading tracking algorithm, the Orientation-Heading Alignment (OHA), which leverages a key insight: people tend to carry smartphones in certain ways due to habits, such as swinging them while walking. For each smartphone attitude during this motion, OHA maps the smartphone orientation to the pedestrian heading and learns such mappings efficiently from coarse headings and smartphone orientations. To anchor our algorithm in a practical scenario, we apply OHA to a challenging task: predicting when pedestrians are about to cross the road to improve road user safety. In particular, using 755 hours of walking data collected since 2020 from 60 individuals, we develop a lightweight model that operates in real-time on commodity devices to predict road crossings. Our evaluation shows that OHA achieves 3.4 times smaller heading errors across nine scenarios than existing methods. Furthermore, OHA enables the early and accurate detection of pedestrian crossing behavior, issuing crossing alerts 0.35 seconds, on average, before pedestrians enter the road range.

eess.SP↗

arXiv2024

Prototypical Partial Optimal Transport for Universal Domain Adaptation

Universal domain adaptation (UniDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain without requiring the same label sets of both domains. The existence of domain and category shift makes the task challenging and requires us to distinguish "known" samples (i.e., samples whose labels exist in both domains) and "unknown" samples (i.e., samples whose labels exist in only one domain) in both domains before reducing the domain gap. In this paper, we consider the problem from the point of view of distribution matching which we only need to align two distributions partially. A novel approach, dubbed mini-batch Prototypical Partial Optimal Transport (m-PPOT), is proposed to conduct partial distribution alignment for UniDA. In training phase, besides minimizing m-PPOT, we also leverage the transport plan of m-PPOT to reweight source prototypes and target samples, and design reweighted entropy loss and reweighted cross-entropy loss to distinguish "known" and "unknown" samples. Experiments on four benchmarks show that our method outperforms the previous state-of-the-art UniDA methods.

cs.CV↗

arXiv2024

Charge-breaking domain walls separating neutral vacua in multi-Higgs models

The scalar potential of a multi-Higgs model can possess a rich structure of minima and saddle points, which evolves in an intricate way as the parameters change. In the hot early Universe, it could trigger multi-step phase transitions, with exotic intermediate phases and peculiar domain wall configurations. Here, we provide a glimpse into this richness with the example of the three-Higgs-doublet model with the symmetry group $Σ(36)$, either exact or softly broken. We present its phase diagram tracking not only the global minimum but all of its extrema. In particular, we reveal parameter space regions in which the deepest saddle point is charge breaking. This naturally leads to phase transitions between neutral vacua which involve expanding and colliding charge-breaking bubble walls. We also comment on opportunities of multi-step phase transitions, on charge-breaking intermediate phases, and on phase transitions between different charge-breaking vacua. We illustrate the general discussion with two benchmark models, one of which possesses competing saddle points and allows for emergence of bubbles of the same true vacuum but with bubble walls of different nature. The intriguing cosmological implications of all these possibilities deserve dedicated study.

hep-ph↗

arXiv2022

Are You Really Muted?: A Privacy Analysis of Mute Buttons in Video Conferencing Apps

Video conferencing apps (VCAs) make it possible for previously private spaces -- bedrooms, living rooms, and kitchens -- into semi-public extensions of the office. For the most part, users have accepted these apps in their personal space without much thought about the permission models that govern the use of their private data during meetings. While access to a device's video camera is carefully controlled, little has been done to ensure the same level of privacy for accessing the microphone. In this work, we ask the question: what happens to the microphone data when a user clicks the mute button in a VCA? We first conduct a user study to analyze users' understanding of the permission model of the mute button. Then, using runtime binary analysis tools, we trace raw audio flow in many popular VCAs as it traverses the app from the audio driver to the network. We find fragmented policies for dealing with microphone data among VCAs -- some continuously monitor the microphone input during mute, and others do so periodically. One app transmits statistics of the audio to its telemetry servers while the app is muted. Using network traffic that we intercept en route to the telemetry server, we implement a proof-of-concept background activity classifier and demonstrate the feasibility of inferring the ongoing background activity during a meeting -- cooking, cleaning, typing, etc. We achieved 81.9% macro accuracy on identifying six common background activities using intercepted outgoing telemetry packets when a user is muted.

cs.CR↗

arXiv2022

DeepHAM: A Global Solution Method for Heterogeneous Agent Models with Aggregate Shocks

An efficient, reliable, and interpretable global solution method, the Deep learning-based algorithm for Heterogeneous Agent Models (DeepHAM), is proposed for solving high dimensional heterogeneous agent models with aggregate shocks. The state distribution is approximately represented by a set of optimal generalized moments. Deep neural networks are used to approximate the value and policy functions, and the objective is optimized over directly simulated paths. In addition to being an accurate global solver, this method has three additional features. First, it is computationally efficient in solving complex heterogeneous agent models, and it does not suffer from the curse of dimensionality. Second, it provides a general and interpretable representation of the distribution over individual states, which is crucial in addressing the classical question of whether and how heterogeneity matters in macroeconomics. Third, it solves the constrained efficiency problem as easily as it solves the competitive equilibrium, which opens up new possibilities for studying optimal monetary and fiscal policies in heterogeneous agent models with aggregate shocks.

econ.GN↗

arXiv2021

Search for topological defect dark matter with a global network of optical magnetometers

Ultralight bosons such as axion-like particles are viable candidates for dark matter. They can form stable, macroscopic field configurations in the form of topological defects that could concentrate the dark matter density into many distinct, compact spatial regions that are small compared to the galaxy but much larger than the Earth. Here, we report the results of a search for transient signals from axion-like particle domain walls with the Global Network of Optical Magnetometers for Exotic physics searches (GNOME). We search the data, consisting of correlated measurements from optical atomic magnetometers located in laboratories all over the world, for patterns of signals propagating through the network consistent with domain walls. The analysis of data from a continuous month-long operation of the GNOME finds no statistically significant signals, thus placing experimental constraints on such dark matter scenarios.

astro-ph.CO↗

arXiv2020

Interpretable Neural Networks for Panel Data Analysis in Economics

The lack of interpretability and transparency are preventing economists from using advanced tools like neural networks in their empirical research. In this paper, we propose a class of interpretable neural network models that can achieve both high prediction accuracy and interpretability. The model can be written as a simple function of a regularized number of interpretable features, which are outcomes of interpretable functions encoded in the neural network. Researchers can design different forms of interpretable functions based on the nature of their tasks. In particular, we encode a class of interpretable functions named persistent change filters in the neural network to study time series cross-sectional data. We apply the model to predicting individual's monthly employment status using high-dimensional administrative data. We achieve an accuracy of 94.5% in the test set, which is comparable to the best performed conventional machine learning methods. Furthermore, the interpretability of the model allows us to understand the mechanism that underlies the prediction: an individual's employment status is closely related to whether she pays different types of insurances. Our work is a useful step towards overcoming the black-box problem of neural networks, and provide a new tool for economists to study administrative and proprietary big data.

econ.EM↗

arXiv2020

The Knowledge Graph for Macroeconomic Analysis with Alternative Big Data

The current knowledge system of macroeconomics is built on interactions among a small number of variables, since traditional macroeconomic models can mostly handle a handful of inputs. Recent work using big data suggests that a much larger number of variables are active in driving the dynamics of the aggregate economy. In this paper, we introduce a knowledge graph (KG) that consists of not only linkages between traditional economic variables but also new alternative big data variables. We extract these new variables and the linkages by applying advanced natural language processing (NLP) tools on the massive textual data of academic literature and research reports. As one example of the potential applications, we use it as the prior knowledge to select variables for economic forecasting models in macroeconomics. Compared to statistical variable selection methods, KG-based methods achieve significantly higher forecasting accuracy, especially for long run forecasts.

econ.GN↗

arXiv2020

All-Optical Single-Species Cesium Atomic Comagnetometer with Optical Free Induction Decay Detection

Atomic comagnetometers, which measure the spin precession frequencies of overlapped species simultaneously, are widely applied to search for exotic spin-dependent interactions. Here we propose and implement an all-optical single-species Cs atomic comagnetometer based on the optical free induction decay (FID) signal of Cs atoms in hyperfine levels $F_g=3~\&~4$ within the same atomic ensemble. We experimentally show that systematic errors induced by magnetic field gradients and laser fields are highly suppressed in the comagnetometer, but those induced by asynchronous optical pumping and drift of residual magnetic field in the shield dominate the uncertainty of the comagnetometer. With this comagnetometer system, we set the constraint on the strength of spin-gravity coupling of the proton at a level of $10^{-18}$ eV, comparable to the most stringent one. With further optimization in magnetic field stabilization and spin polarization, the systematic errors can be effectively suppressed, and signal-to-noise ratio (SNR) can be improved, promising to set more stringent constraints on spin-gravity interactions.

physics.atom-ph↗