arXiv subjects

Hyejin Kim

Publications and source records attributed to Hyejin Kim.

8 recordsLinked to original sources

arXiv2026

Reselection in the game of best choice

We investigate a remarkable probability distribution on the symmetric group, due to Steck from the early 1970's, arising from a natural process that intertwines continuous and discrete selections for the values and positions, respectively, of a permutation. Steck used a matrix determinant to express his distribution, whereas we contribute new combinatorial formulas for it in terms of "bottom-to-top maxima" (that are simply the left-to-right maxima of the inverse) permutation statistics. These formulas specialize, in the case of the identity permutation, to a result of Pitman--Stanley from the late 1990's. We then use the Steck distribution to define a game of best choice (secretary problem variation) that incorporates a filtering process for the pool of candidates over time. We solve the model for the case where there is a single filtering step. It turns out that the probability of winning the game under optimal play is similar to the classical model ($1/e$, asymptotically), but that the interviewer must employ a different (non-positional) strategy in order to attain it. The optimal strategy depends on the relationship between interview position and the next bottom-to-top maximum value after the filtering step. Among other results, we prove that the optimal strategy always transitions from rejection to acceptance between positions $(1/e)$ and $(1/e) + (1 - 1/e)y$ as a proportion of the total candidates considered, where $y$ is the proportion of unfiltered candidates.

math.CO↗

arXiv2026

Learning from almost nothing: How neural networks survive heavy input corruption

Learning from imperfect data is a central theme in machine learning, connecting practical questions of robustness to fundamental questions of learnability. Here we examine attribute noise: learning from corrupted inputs while keeping the labels intact, a setting that has received considerably less analytical attention than its label-noise counterpart. We consider two types of corruption models: additive noise and replacement noise. Through experiments with multi-layer perceptrons (MLPs) on corrupted classification datasets, we find that neural networks remain robust, maintaining well-above-chance accuracy even when inputs are >90% corrupted -- far beyond human recognition. To understand this robustness, we analyze infinite-width networks in the heavy-corruption regime using a mean-field-inspired approach and derive a leading-order decision rule for the classification outcome: the network implements a prototype rule, the nearest-class-mean, assigning each test point to the class whose training-set average it most closely resembles. This leading-order decision rule is universal across a broad range of MLP architectures, holding for any depth, as well as a wide class of activation functions and noise distributions. The same centroid mechanism closely matches finite-width network behavior in our experiments and provides an interpretable and analytically tractable account of why learning can succeed even when individual training examples carry almost no signal.

cs.LG↗

arXiv2025

Learning measurement-induced phase transitions using attention

Measurement-induced phase transitions (MIPTs) epitomize new intellectual pursuits inspired by the advent of quantum hardware and the emergence of discrete and programmable circuit dynamics. Nevertheless, experimentally observing this transition is challenging, often requiring non-scalable protocols, such as post-selecting measurement trajectories or relying on classical simulations. We introduce a scalable data-centric approach using Quantum Attention Networks (QuAN) to detect MIPTs without requiring post-selection or classical simulation. Applying QuAN to dynamics generated by Haar random unitaries and weak measurements, we first demonstrate that it can pinpoint MIPTs using their interpretation as "learnability" transitions, where it becomes possible to distinguish two different initial states from the measurement record, locating a phase boundary consistent with exact results. Motivated by sample efficiency, we consider an alternative "phase recognition" task-classifying weak- and strong-monitoring data generated from a single initial state. We find QuAN can provide an efficient and noise-tolerant upper bound on the MIPT based on measurement data alone by coupling Born-distribution-level (inter-trajectory) and dynamical (temporal) attention. In particular, our inspection of the inter-trajectory scores of the model trained with minimal sample size processing test data confirmed that QuAN paid special attention to the tail of the distribution of the Born probabilities at early times. This reassuring interpretation of QuAN's learning implies the phase-recognition approach can meaningfully signal MIPT in an experimentally accessible manner. Our results lay the groundwork for observing MIPT on near-term quantum hardware and highlight attention-based architectures as powerful tools for learning complex quantum dynamics.

quant-ph↗

arXiv2024

Attention to Quantum Complexity

The imminent era of error-corrected quantum computing urgently demands robust methods to characterize complex quantum states, even from limited and noisy measurements. We introduce the Quantum Attention Network (QuAN), a versatile classical AI framework leveraging the power of attention mechanisms specifically tailored to address the unique challenges of learning quantum complexity. Inspired by large language models, QuAN treats measurement snapshots as tokens while respecting their permutation invariance. Combined with a novel parameter-efficient mini-set self-attention block (MSSAB), such data structure enables QuAN to access high-order moments of the bit-string distribution and preferentially attend to less noisy snapshots. We rigorously test QuAN across three distinct quantum simulation settings: driven hard-core Bose-Hubbard model, random quantum circuits, and the toric code under coherent and incoherent noise. QuAN directly learns the growth in entanglement and state complexity from experimentally obtained computational basis measurements. In particular, it learns the growth in complexity of random circuit data upon increasing depth from noisy experimental data. Taken to a regime inaccessible by existing theory, QuAN unveils the complete phase diagram for noisy toric code data as a function of both noise types. This breakthrough highlights the transformative potential of using purposefully designed AI-driven solutions to assist quantum hardware.

quant-ph↗

arXiv2021

6G: from Densification to Diversification

The 5G system has finally begun commercialization, and now is the time to start discussing the road map for the 6G system. While the 5G system was designed with a focus on discovering new service types for high speed, low-latency, and massive connective services, the evolution of the network interface for 6G should be considered with an eye toward supporting these complicated communication environments. As machine-driven data traffic continues to increase exponentially, 6G must be able to support a series of connection methods that did not previously exist. In departure from base-station-oriented cell densification, network diversification is necessary if we are to satisfy the comprehensive requirements of end terminals for diverse applications. In this article, we predict what will drive 6G and look at what key requirements should be considered in 6G. We then diversify four types of network architectures according to link characteristics, communication ranges, and target services. The four types of networks play complementary roles while at the same time collaborating across the entire 6G network. Lastly, we call attention to key technologies and challenges in the air, network, and assistive technologies that will have to be addressed when designing the 6G system.

cs.NI↗

arXiv2020

2018 Robotic Scene Segmentation Challenge

In 2015 we began a sub-challenge at the EndoVis workshop at MICCAI in Munich using endoscope images of ex-vivo tissue with automatically generated annotations from robot forward kinematics and instrument CAD models. However, the limited background variation and simple motion rendered the dataset uninformative in learning about which techniques would be suitable for segmentation in real surgery. In 2017, at the same workshop in Quebec we introduced the robotic instrument segmentation dataset with 10 teams participating in the challenge to perform binary, articulating parts and type segmentation of da Vinci instruments. This challenge included realistic instrument motion and more complex porcine tissue as background and was widely addressed with modifications on U-Nets and other popular CNN architectures. In 2018 we added to the complexity by introducing a set of anatomical objects and medical devices to the segmented classes. To avoid over-complicating the challenge, we continued with porcine data which is dramatically simpler than human tissue due to the lack of fatty tissue occluding many organs.

cs.CV↗

arXiv2017

Orthogonal Code-based Block Transmission for Burst Transmission

This paper proposes a new multi-carrier system, called orthogonal code-based block transmission (OCBT). OCBT applies a time-spreading method with an orthogonal code to have a block signal structure and a windowing procedure to reduce the out-of-band (OOB) radiation. The proposed OCBT can transmit the quadrature amplitude modulation (QAM) signals to use the conventional multiple input multiple output techniques. Numerical results show that the proposed OCBT using QAM signal has the short burst compared to the filter-bank multi-carrier (FBMC), the low complexity compared to FBMC and windowed orthogonal frequency division multiplexing (W-OFDM) and also the low OOB radiation compared to OFDM.

cs.IT↗

arXiv2016

Rapidly Computing Sparse Legendre Expansions via Sparse Fourier Transforms

In this paper we propose a general strategy for rapidly computing sparse Legendre expansions. The resulting methods yield a new class of fast algorithms capable of approximating a given function $f:[-1,1] \rightarrow \mathbb{R}$ with a near-optimal linear combination of $s$ Legendre polynomials of degree $\leq N$ in just $(s \log N)^{\mathcal{O}(1)}$-time. When $s \ll N$ these algorithms exhibit sublinear runtime complexities in $N$, as opposed to traditional $Ω(N \log N)$-time methods for computing all of the first $N$ Legendre coefficients of $f$. Theoretical as well as numerical results demonstrate the promise of the proposed approach.

math.NA↗