arXiv subjects

Yushen Huang

Publications and source records attributed to Yushen Huang.

8 recordsLinked to original sources

arXiv2025

Prototype-Driven Adaptation for Few-Shot Object Detection

Few-shot object detection (FSOD) often suffers from base-class bias and unstable calibration when only a few novel samples are available. We propose Prototype-Driven Alignment (PDA), a lightweight, plug-in metric head for DeFRCN that provides a prototype-based "second opinion" complementary to the linear classifier. PDA maintains support-only prototypes in a learnable identity-initialized projection space and optionally applies prototype-conditioned RoI alignment to reduce geometric mismatch. During fine-tuning, prototypes can be adapted via exponential moving average(EMA) updates on labeled foreground RoIs-without introducing class-specific parameters-and are frozen at inference to ensure strict protocol compliance. PDA employs a best-of-K matching scheme to capture intra-class multi-modality and temperature-scaled fusion to combine metric similarities with detector logits. Experiments on VOC FSOD and GFSOD benchmarks show that PDA consistently improves novel-class performance with minimal impact on base classes and negligible computational overhead.

cs.CV↗

arXiv2025

Fast online node labeling with graph subsampling

Large data applications rely on storing data in massive, sparse graphs with millions to trillions of nodes. Graph-based methods, such as node prediction, aim for computational efficiency regardless of graph size. Techniques like localized approximate personalized page rank (APPR) solve sparse linear systems with complexity independent of graph size, but is in terms of the maximum node degree, which can be much larger in practice than the average node degree for real-world large graphs. In this paper, we consider an \emph{online subsampled APPR method}, where messages are intentionally dropped at random. We use tools from graph sparsifiers and matrix linear algebra to give approximation bounds on the graph's spectral properties ($O(1/ε^2)$ edges), and node classification performance (added $O(nε)$ overhead).

cs.DS↗

arXiv2025

Proximal Flow Inspired Multi-Step Methods

We investigate a family of approximate multi-step proximal point methods, framed as implicit linear discretizations of gradient flow. The resulting methods are multi-step proximal point methods, with similar computational cost in each update as the proximal point method. We explore several optimization methods where applying an approximate multistep proximal points method results in improved convergence behavior. We also include convergence analysis for the proposed method in several problem settings: quadratic problems, general problems that are strongly or weakly (non)convex, and accelerated results for alternating projections.

math.OC↗

arXiv2024

Reachability Analysis for Linear Systems with Uncertain Parameters using Polynomial Zonotopes

In real world applications, uncertain parameters are the rule rather than the exception. We present a reachability algorithm for linear systems with uncertain parameters and inputs using set propagation of polynomial zonotopes. In contrast to previous methods, our approach is able to tightly capture the non-convexity of the reachable set. Building up on our main result, we show how our reachability algorithm can be extended to handle linear time-varying systems as well as linear systems with time-varying parameters. Moreover, our approach opens up new possibilities for reachability analysis of linear time-invariant systems, nonlinear systems, and hybrid systems. We compare our approach to other state of the art methods, with superior tightness on two benchmarks including a 9-dimensional vehicle platooning system. Moreover, as part of the journal extension, we investigate through a polynomial zonotope with special structure named multi-affine zonotopes and its optimization problem. We provide the corresponding optimization algorithm and experiment over the examples obatined from two benchmark systems, showing the efficiency and scalability comparing to the state of the art method for handling such type of set representation.

eess.SY↗

arXiv2023

Fast American Option Pricing using Nonlinear Stencils

We study the binomial, trinomial, and Black-Scholes-Merton models of option pricing. We present fast parallel discrete-time finite-difference algorithms for American call option pricing under the binomial and trinomial models and American put option pricing under the Black-Scholes-Merton model. For $T$-step finite differences, each algorithm runs in $O(\left(T\log^2{T}\right)/p + T)$ time under a greedy scheduler on $p$ processing cores, which is a significant improvement over the $Θ({T^2}/{p}) + Ω(T\log{T})$ time taken by the corresponding state-of-the-art parallel algorithm. Even when run on a single core, the $O(T\log^2{T})$ time taken by our algorithms is asymptotically much smaller than the $Θ(T^2)$ running time of the fastest known serial algorithms. Implementations of our algorithms significantly outperform the fastest implementations of existing algorithms in practice, e.g., when run for $T \approx 1000$ steps on a 48-core machine, our algorithm for the binomial model runs at least $15\times$ faster than the fastest existing parallel program for the same model with the speed-up factor gradually reaching beyond $500\times$ for $T \approx 0.5 \times 10^6$. It saves more than 80\% energy when $T \approx 4000$, and more than 99\% energy for $T > 60,000$. Our option pricing algorithms can be viewed as solving a class of nonlinear 1D stencil (i.e., finite-difference) computation problems efficiently using the Fast Fourier Transform (FFT). To our knowledge, ours are the first algorithms to handle such stencils in $o(T^2)$ time. These contributions are of independent interest as stencil computations have a wide range of applications beyond quantitative finance.

cs.CE↗

arXiv2023

Follow the flow: Proximal flow inspired multi-step methods

We investigate a family of approximate multi-step proximal point methods, accelerated by implicit linear discretizations of gradient flow. The resulting methods are multi-step proximal point methods, with similar computational cost in each update as the proximal point method. We explore several optimization methods where applying an approximate multistep proximal points method results in improved convergence behavior. We argue that this is the result of the lowering of truncation error in approximating gradient flow

math.OC↗

arXiv2023

Unraveling Managerial Tangents in Firm Disclosure: Concealing Issues or Being Exposed?

Earnings calls influence stock prices and are traditionally analyzed using sentiment and linguistic traces. Our research introduces a "Topic-Switching Index," a novel metric quantified through the transformer model FinBERT, to measure managerial evasion during Q$\&$A sessions in earnings calls. We find a negative correlation between this index and subsequent stock prices, indicating that investors penalize managerial evasiveness. This study is the first to quantify such evasive tactics, adding a new dimension to how earnings calls are understood and suggesting that topic shifting is an overlooked but significant factor. We also show the predictability of the index under three different classifier models and it stands out in all circumstances.

cs.CE↗

arXiv2023

On the Difficulty of Intersection Checking with Polynomial Zonotopes

Polynomial zonotopes, a non-convex set representation, have a wide range of applications from real-time motion planning and control in robotics, to reachability analysis of nonlinear systems and safety shielding in reinforcement learning. Despite this widespread use, a frequently overlooked difficulty associated with polynomial zonotopes is intersection checking. Determining whether the reachable set, represented as a polynomial zonotope, intersects an unsafe set is not straightforward. In fact, we show that this fundamental operation is NP-hard, even for a simple class of polynomial zonotopes. The standard method for intersection checking with polynomial zonotopes is a two-part algorithm that overapproximates a polynomial zonotope with a regular zonotope and then, if the overapproximation error is deemed too large, splits the set and recursively tries again. Beyond the possible need for a large number of splits, we identify two sources of concern related to this algorithm: (1) overapproximating a polynomial zonotope with a zonotope has unbounded error, and (2) after splitting a polynomial zonotope, the overapproximation error can actually increase. Taken together, this implies there may be a possibility that the algorithm does not always terminate.We perform a rigorous analysis of the method and detail necessary conditions for the union of overapproximations to provably converge to the original polynomial zonotope.

eess.SY↗