arXiv subjects

Junwen Yao

Publications and source records attributed to Junwen Yao.

6 recordsLinked to original sources

arXiv2026

STELLAR: Scaling 3D Perception Large Models for Autonomous Driving

Model scaling has demonstrated remarkable success through large-scale training on diverse datasets. It remains an open question whether the same paradigm would apply to autonomous driving perception systems due to unique challenges, such as fusing heterogeneous sensor data and the need for sophisticated 3D spatial understanding. To bridge this gap, we present a comprehensive study on systematically analyzing the impact of scale on these systems. We develop our STELLAR model based on Sparse Window Transformer, by extending the input modalities to include LiDAR, radar, camera, and map prior. We train the model on a large-scale dataset of 50 million driving examples with up to 500 million parameters. Our large-scale experiments reveal empirical scaling trends that connect model performance to model size, data, and compute. The resulting model establishes a new state-of-the-art on the Waymo Open Dataset challenge, outperforming prior arts by a large margin. Our work demonstrates that large-scale training is a highly promising path for advancing the capabilities of perception models for autonomous driving.

cs.CV↗

arXiv2025

Optimal Smooth Coverage Trajectory Planning for Quadrotors in Cluttered Environment

For typical applications of UAVs in power grid scenarios, we construct the problem as planning UAV trajectories for coverage in cluttered environments. In this paper, we propose an optimal smooth coverage trajectory planning algorithm. The algorithm consists of two stages. In the front-end, a Genetic Algorithm (GA) is employed to solve the Traveling Salesman Problem (TSP) for Points of Interest (POIs), generating an initial sequence of optimized visiting points. In the back-end, the sequence is further optimized by considering trajectory smoothness, time consumption, and obstacle avoidance. This is formulated as a nonlinear least squares problem and solved to produce a smooth coverage trajectory that satisfies these constraints. Numerical simulations validate the effectiveness of the proposed algorithm, ensuring UAVs can smoothly cover all POIs in cluttered environments.

cs.RO↗

arXiv2023

Error Estimation for Random Fourier Features

Random Fourier Features (RFF) is among the most popular and broadly applicable approaches for scaling up kernel methods. In essence, RFF allows the user to avoid costly computations on a large kernel matrix via a fast randomized approximation. However, a pervasive difficulty in applying RFF is that the user does not know the actual error of the approximation, or how this error will propagate into downstream learning tasks. Up to now, the RFF literature has primarily dealt with these uncertainties using theoretical error bounds, but from a user's standpoint, such results are typically impractical -- either because they are highly conservative or involve unknown quantities. To tackle these general issues in a data-driven way, this paper develops a bootstrap approach to numerically estimate the errors of RFF approximations. Three key advantages of this approach are: (1) The error estimates are specific to the problem at hand, avoiding the pessimism of worst-case bounds. (2) The approach is flexible with respect to different uses of RFF, and can even estimate errors in downstream learning tasks. (3) The approach enables adaptive computation, so that the user can quickly inspect the error of a rough initial kernel approximation and then predict how much extra work is needed. Lastly, in exchange for all of these benefits, the error estimates can be obtained at a modest computational cost.

stat.ML↗

arXiv2022

Rates of Bootstrap Approximation for Eigenvalues in High-Dimensional PCA

In the context of principal components analysis (PCA), the bootstrap is commonly applied to solve a variety of inference problems, such as constructing confidence intervals for the eigenvalues of the population covariance matrix $Σ$. However, when the data are high-dimensional, there are relatively few theoretical guarantees that quantify the performance of the bootstrap. Our aim in this paper is to analyze how well the bootstrap can approximate the joint distribution of the leading eigenvalues of the sample covariance matrix $\hatΣ$, and we establish non-asymptotic rates of approximation with respect to the multivariate Kolmogorov metric. Under certain assumptions, we show that the bootstrap can achieve the dimension-free rate of ${\tt{r}}(Σ)/\sqrt n$ up to logarithmic factors, where ${\tt{r}}(Σ)$ is the effective rank of $Σ$, and $n$ is the sample size. From a methodological standpoint, our work also illustrates that applying a transformation to the eigenvalues of $\hatΣ$ before bootstrapping is an important consideration in high-dimensional settings.

math.ST↗

arXiv2021

A Sharp Lower-tail Bound for Gaussian Maxima with Application to Bootstrap Methods in High Dimensions

Although there is an extensive literature on the maxima of Gaussian processes, there are relatively few non-asymptotic bounds on their lower-tail probabilities. The aim of this paper is to develop such a bound, while also allowing for many types of dependence. Let $(ξ_1,\dots,ξ_N)$ be a centered Gaussian vector with standardized entries, whose correlation matrix $R$ satisfies $\max_{i\neq j} R_{ij}\leq ρ_0$ for some constant $ρ_0\in (0,1)$. Then, for any $ε_0\in(0,\sqrt{1-ρ_0})$, we establish an upper bound on the probability $\mathbb{P}(\max_{1\leq j\leq N} ξ_j\leq ε_0\sqrt{2\log(N)})$ in terms of $(ρ_0,ε_0,N)$. The bound is also sharp, in the sense that it is attained up to a constant, independent of $N$. Next, we apply this result in the context of high-dimensional statistics, where we simplify and weaken conditions that have recently been used to establish near-parametric rates of bootstrap approximation. Lastly, an interesting aspect of this application is that it makes use of recent refinements of Bourgain and Tzafriri's "restricted invertibility principle".

math.PR↗

arXiv2021

Deep Learning for Functional Data Analysis with Adaptive Basis Layers

Despite their widespread success, the application of deep neural networks to functional data remains scarce today. The infinite dimensionality of functional data means standard learning algorithms can be applied only after appropriate dimension reduction, typically achieved via basis expansions. Currently, these bases are chosen a priori without the information for the task at hand and thus may not be effective for the designated task. We instead propose to adaptively learn these bases in an end-to-end fashion. We introduce neural networks that employ a new Basis Layer whose hidden units are each basis functions themselves implemented as a micro neural network. Our architecture learns to apply parsimonious dimension reduction to functional inputs that focuses only on information relevant to the target rather than irrelevant variation in the input function. Across numerous classification/regression tasks with functional data, our method empirically outperforms other types of neural networks, and we prove that our approach is statistically consistent with low generalization error. Code is available at: \url{https://github.com/jwyyy/AdaFNN}.

stat.ML↗