Author name cluster

Hyeji Kim

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

14 papers

2 author rows

ICLR Conference 2025 Conference Paper

Attention with Markov: A Curious Case of Single-layer Transformers

Ashok Vardhan Makkuva
Marco Bondaschi
Adway Girish
Alliot Nagle
Martin Jaggi
Hyeji Kim
Michael Gastpar

Attention-based transformers have achieved tremendous success across a variety of disciplines including natural languages. To deepen our understanding of their sequential modeling capabilities, there is a growing interest in using Markov input processes to study them. A key finding is that when trained on first-order Markov chains, transformers with two or more layers consistently develop an induction head mechanism to estimate the in-context bigram conditional distribution. In contrast, single-layer transformers, unable to form an induction head, directly learn the Markov kernel but often face a surprising challenge: they become trapped in local minima representing the unigram distribution, whereas deeper models reliably converge to the ground-truth bigram. While single-layer transformers can theoretically model first-order Markov chains, their empirical failure to learn this simple kernel in practice remains a curious phenomenon. To explain this contrasting behavior of single-layer models, in this paper we introduce a new framework for a principled analysis of transformers via Markov chains. Leveraging our framework, we theoretically characterize the loss landscape of single-layer transformers and show the existence of global minima (bigram) and bad local minima (unigram) contingent on data properties and model architecture. We precisely delineate the regimes under which these local optima occur. Backed by experiments, we demonstrate that our theoretical findings are in congruence with the empirical results. Finally, we outline several open problems in this arena.

Details

NeurIPS Conference 2025 Conference Paper

Generating Informative Samples for Risk-Averse Fine-Tuning of Downstream Tasks

Heasung Kim
Taekyun Lee
Hyeji Kim
Gustavo De Veciana

Risk-averse modeling is critical in safety-sensitive and high-stakes applications. Conditional Value-at-Risk (CVaR) quantifies such risk by measuring the expected loss in the tail of the loss distribution, and minimizing it provides a principled framework for training robust models. However, direct CVaR minimization remains challenging due to the difficulty of accurately estimating rare, high-loss events—particularly at extreme quantiles. In this work, we propose a novel training framework that synthesizes informative samples for CVaR optimization using score-based generative models. Specifically, we guide a diffusion-based generative model to sample from a reweighted distribution that emphasizes inputs likely to incur high loss under a pretrained reference model. These samples are then incorporated via a loss-weighted importance sampling scheme to reduce noise in stochastic optimization. We establish convergence guarantees and show that the synthesized, high-loss-emphasized dataset substantially contributes to the noise reduction. Empirically, we validate the effectiveness of our approach across multiple settings, including a real-world wireless channel compression task, where our method achieves significant improvements over standard risk minimization strategies.

PDF Details

ICML Conference 2024 Conference Paper

Clustered Federated Learning via Gradient-based Partitioning

Heasung Kim
Hyeji Kim
Gustavo de Veciana

Clustered Federated Learning (CFL) is a promising distributed learning framework that addresses data heterogeneity issues across multiple clients by grouping clients and providing a shared generalized model for each group. However, under privacy-preserving federated learning protocols where there is no direct sharing of clients’ local datasets, existing approaches often fail to find optimal client groupings resulting in sub-optimal performance. In this paper, we propose a novel CFL algorithm that achieves robust clustering and learning performance. Conceptually, our algorithm groups clients that exhibit similarity in their model updates by periodically accumulating and clustering the gradients that clients compute for various models. The proposed algorithm is shown to achieve a near-optimal error rate for stochastic convergence to optimal models under mild conditions. We present a detailed analysis of the algorithm along with an evaluation on several CFL benchmarks demonstrating that it outperforms existing approaches in terms of convergence speed, clustering accuracy, and task performance.

Details

ICML Conference 2024 Conference Paper

DeepPolar: Inventing Nonlinear Large-Kernel Polar Codes via Deep Learning

S. Ashwin Hebbar
Sravan Kumar Ankireddy
Hyeji Kim
Sewoong Oh
Pramod Viswanath

Progress in designing channel codes has been driven by human ingenuity and, fittingly, has been sporadic. Polar codes, developed on the foundation of Arikan’s polarization kernel, represent the latest breakthrough in coding theory and have emerged as the state-of-the-art error-correction code for short-to-medium block length regimes. In an effort to automate the invention of good channel codes, especially in this regime, we explore a novel, non-linear generalization of Polar codes, which we call DeepPolar codes. DeepPolar codes extend the conventional Polar coding framework by utilizing a larger kernel size and parameterizing these kernels and matched decoders through neural networks. Our results demonstrate that these data-driven codes effectively leverage the benefits of a larger kernel size, resulting in enhanced reliability when compared to both existing neural codes and conventional Polar codes.

Details

NeurIPS Conference 2024 Conference Paper

Fundamental Limits of Prompt Compression: A Rate-Distortion Framework for Black-Box Language Models

Alliot Nagle
Adway Girish
Marco Bondaschi
Michael Gastpar
Ashok Vardhan Makkuva
Hyeji Kim

We formalize the problem of prompt compression for large language models (LLMs) and present a framework to unify token-level prompt compression methods which create hard prompts for black-box models. We derive the distortion-rate function for this setup as a linear program, and provide an efficient algorithm to compute this fundamental limit via the dual of the linear program. Using the distortion-rate function as the baseline, we study the performance of existing compression schemes on a synthetic dataset consisting of prompts generated from a Markov chain, natural language queries, and their respective answers. Our empirical analysis demonstrates the criticality of query-aware prompt compression, where the compressor has knowledge of the downstream task/query for the black-box LLM. We show that there is a large gap between the performance of current prompt compression methods and the optimal strategy, and propose Adaptive QuerySelect, a query-aware, variable-rate adaptation of a prior work to close the gap. We extend our experiments to a small natural language dataset to further confirm our findings on our synthetic dataset.

PDF Details DOI

ICML Conference 2024 Conference Paper

LASER: Linear Compression in Wireless Distributed Optimization

Ashok Vardhan Makkuva
Marco Bondaschi
Thijs Vogels
Martin Jaggi
Hyeji Kim
Michael Gastpar

Data-parallel SGD is the de facto algorithm for distributed optimization, especially for large scale machine learning. Despite its merits, communication bottleneck is one of its persistent issues. Most compression schemes to alleviate this either assume noiseless communication links, or fail to achieve good performance on practical tasks. In this paper, we close this gap and introduce LASER: L ine A r Compre S sion in Wir E less Dist R ibuted Optimization. LASER capitalizes on the inherent low-rank structure of gradients and transmits them efficiently over the noisy channels. Whilst enjoying theoretical guarantees similar to those of the classical SGD, LASER shows consistent gains over baselines on a variety of practical benchmarks. In particular, it outperforms the state-of-the-art compression schemes on challenging computer vision and GPT language modeling tasks. On the latter, we obtain 50-64% improvement in perplexity over our baselines for noisy channels.

Details

NeurIPS Conference 2024 Conference Paper

Local to Global: Learning Dynamics and Effect of Initialization for Transformers

Ashok V. Makkuva
Marco Bondaschi
Chanakya Ekbote
Adway Girish
Alliot Nagle
Hyeji Kim
Michael Gastpar

In recent years, transformer-based models have revolutionized deep learning, particularly in sequence modeling. To better understand this phenomenon, there is a growing interest in using Markov input processes to study transformers. However, our current understanding in this regard remains limited with many fundamental questions about how transformers learn Markov chains still unanswered. In this paper, we address this by focusing on first-order Markov chains and single-layer transformers, providing a comprehensive characterization of the learning dynamics in this context. Specifically, we prove that transformer parameters trained on next-token prediction loss can either converge to global or local minima, contingent on the initialization and the Markovian data properties, and we characterize the precise conditions under which this occurs. To the best of our knowledge, this is the first result of its kind highlighting the role of initialization. We further demonstrate that our theoretical findings are corroborated by empirical evidence. Based on these insights, we provide guidelines for the initialization of single-layer transformers and demonstrate their effectiveness. Finally, we outline several open problems in this arena. Code is available at: \url{https: //github. com/Bond1995/Markov}.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Neural Cover Selection for Image Steganography

Karl Chahine
Hyeji Kim

In steganography, selecting an optimal cover image—referred to as cover selection—is pivotal for effective message concealment. Traditional methods have typically employed exhaustive searches to identify images that conform to specific perceptual or complexity metrics. However, the relationship between these metrics and the actual message hiding efficacy of an image is unclear, often yielding less-than-ideal steganographic outcomes. Inspired by recent advancements in generative models, we introduce a novel cover selection framework, which involves optimizing within the latent space of pretrained generative models to identify the most suitable cover images, distinguishing itself from traditional exhaustive search methods. Our method shows significant advantages in message recovery and image quality. We also conduct an information-theoretic analysis of the generated cover images, revealing that message hiding predominantly occurs in low-variance pixels, reflecting the waterfilling algorithm's principles in parallel Gaussian channels.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

Task-aware Distributed Source Coding under Dynamic Bandwidth

Po-han Li
Sravan Kumar Ankireddy
Ruihan (Philip) Zhao
Hossein Nourkhiz Mahjoub
Ehsan Moradi Pari
Ufuk Topcu
Sandeep Chinchali
Hyeji Kim

Efficient compression of correlated data is essential to minimize communication overload in multi-sensor networks. In such networks, each sensor independently compresses the data and transmits them to a central node. A decoder at the central node decompresses and passes the data to a pre-trained machine learning-based task model to generate the final output. Due to limited communication bandwidth, it is important for the compressor to learn only the features that are relevant to the task. Additionally, the final performance depends heavily on the total available bandwidth. In practice, it is common to encounter varying availability in bandwidth. Since higher bandwidth results in better performance, it is essential for the compressor to dynamically take advantage of the maximum available bandwidth at any instant. In this work, we propose a novel distributed compression framework composed of independent encoders and a joint decoder, which we call neural distributed principal component analysis (NDPCA). NDPCA flexibly compresses data from multiple sources to any available bandwidth with a single model, reducing compute and storage overhead. NDPCA achieves this by learning low-rank task representations and efficiently distributing bandwidth among sensors, thus providing a graceful trade-off between performance and bandwidth. Experiments show that NDPCA improves the success rate of multi-view robotic arm manipulation by 9% and the accuracy of object detection tasks on satellite imagery by 14% compared to an autoencoder with uniform bandwidth allocation.

PDF Details

NeurIPS Conference 2021 Conference Paper

A Channel Coding Benchmark for Meta-Learning

Rui Li
Ondrej Bohdal
Rajesh K Mishra
Hyeji Kim
Da Li
Nicholas Lane
Timothy Hospedales

Meta-learning provides a popular and effective family of methods for data-efficient learning of new tasks. However, several important issues in meta-learning have proven hard to study thus far. For example, performance degrades in real-world settings where meta-learners must learn from a wide and potentially multi-modal distribution of training tasks; and when distribution shift exists between meta-train and meta-test task distributions. These issues are typically hard to study since the shape of task distributions, and shift between them are not straightforward to measure or control in standard benchmarks. We propose the channel coding problem as a benchmark for meta-learning. Channel coding is an important practical application where task distributions naturally arise, and fast adaptation to new tasks is practically valuable. We use this benchmark to study several aspects of meta-learning, including the impact of task distribution breadth and shift on meta-learner performance, which can be controlled in the coding problem. Going forward, this benchmark provides a tool for the community to study the capabilities and limitations of meta-learning, and to drive research on practically robust and effective meta-learners.

PDF Details

NeurIPS Conference 2020 Conference Paper

BRP-NAS: Prediction-based NAS using GCNs

Lukasz Dudziak
Thomas Chau
Mohamed Abdelfattah
Royson Lee
Hyeji Kim
Nicholas Lane

Neural architecture search (NAS) enables researchers to automatically explore broad design spaces in order to improve efficiency of neural networks. This efficiency is especially important in the case of on-device deployment, where improvements in accuracy should be balanced out with computational demands of a model. In practice, performance metrics of model are computationally expensive to obtain. Previous work uses a proxy (e. g. , number of operations) or a layer-wise measurement of neural network layers to estimate end-to-end hardware performance but the imprecise prediction diminishes the quality of NAS. To address this problem, we propose BRP-NAS, an efficient hardware-aware NAS enabled by an accurate performance predictor-based on graph convolutional network (GCN). What is more, we investigate prediction quality on different metrics and show that sample efficiency of the predictor-based NAS can be improved by considering binary relations of models and an iterative data selection strategy. We show that our proposed method outperforms all prior methods on NAS-Bench-101, NAS-Bench-201 and DARTS. Finally, to raise awareness of the fact that accurate latency estimation is not a trivial task, we release LatBench -- a latency dataset of NAS-Bench-201 models running on a broad range of devices.

PDF Details

NeurIPS Conference 2019 Conference Paper

Turbo Autoencoder: Deep learning based channel codes for point-to-point communication channels

Yihan Jiang
Hyeji Kim
Himanshu Asnani
Sreeram Kannan
Sewoong Oh
Pramod Viswanath

Designing codes that combat the noise in a communication medium has remained a significant area of research in information theory as well as wireless communications. Asymptotically optimal channel codes have been developed by mathematicians for communicating under canonical models after over 60 years of research. On the other hand, in many non-canonical channel settings, optimal codes do not exist and the codes designed for canonical models are adapted via heuristics to these channels and are thus not guaranteed to be optimal. In this work, we make significant progress on this problem by designing a fully end-to-end jointly trained neural encoder and decoder, namely, Turbo Autoencoder (TurboAE), with the following contributions: (a) under moderate block lengths, TurboAE approaches state-of-the-art performance under canonical channels; (b) moreover, TurboAE outperforms the state-of-the-art codes under non-canonical settings in terms of reliability. TurboAE shows that the development of channel coding design can be automated via deep learning, with near-optimal performance.

PDF Details

NeurIPS Conference 2018 Conference Paper

Deepcode: Feedback Codes via Deep Learning

Hyeji Kim
Yihan Jiang
Sreeram Kannan
Sewoong Oh
Pramod Viswanath

The design of codes for communicating reliably over a statistically well defined channel is an important endeavor involving deep mathematical research and wide- ranging practical applications. In this work, we present the first family of codes obtained via deep learning, which significantly beats state-of-the-art codes designed over several decades of research. The communication channel under consideration is the Gaussian noise channel with feedback, whose study was initiated by Shannon; feedback is known theoretically to improve reliability of communication, but no practical codes that do so have ever been successfully constructed. We break this logjam by integrating information theoretic insights harmoniously with recurrent-neural-network based encoders and decoders to create novel codes that outperform known codes by 3 orders of magnitude in reliability. We also demonstrate several desirable properties in the codes: (a) generalization to larger block lengths; (b) composability with known codes; (c) adaptation to practical constraints. This result also presents broader ramifications to coding theory: even when the channel has a clear mathematical model, deep learning methodologies, when combined with channel specific information-theoretic insights, can potentially beat state-of-the-art codes, constructed over decades of mathematical research.

PDF Details

NeurIPS Conference 2017 Conference Paper

Discovering Potential Correlations via Hypercontractivity

Hyeji Kim
Weihao Gao
Sreeram Kannan
Sewoong Oh
Pramod Viswanath

Discovering a correlation from one variable to another variable is of fundamental scientific and practical interest. While existing correlation measures are suitable for discovering average correlation, they fail to discover hidden or potential correlations. To bridge this gap, (i) we postulate a set of natural axioms that we expect a measure of potential correlation to satisfy; (ii) we show that the rate of information bottleneck, i. e. , the hypercontractivity coefficient, satisfies all the proposed axioms; (iii) we provide a novel estimator to estimate the hypercontractivity coefficient from samples; and (iv) we provide numerical experiments demonstrating that this proposed estimator discovers potential correlations among various indicators of WHO datasets, is robust in discovering gene interactions from gene expression time series data, and is statistically more powerful than the estimators for other correlation measures in binary hypothesis testing of canonical examples of potential correlations.

PDF Details