Author name cluster

Youngseog Chung

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.

6 papers

2 author rows

TMLR Journal 2025 Journal Article

Beyond Parameter Count: Implicit Bias in Soft Mixture of Experts

Youngseog Chung
Dhruv Malik
Jeff Schneider
Yuanzhi Li
Aarti Singh

The traditional viewpoint on Sparse Mixture of Experts (MoE) models is that instead of training a single _large_ expert, which is computationally expensive, we can train many _small_ experts. The hope is that if the total parameter count of the small experts equals that of the singular large expert, then we retain the representation power of the large expert while gaining computational tractability and promoting expert specialization. The recently introduced Soft MoE replaces the Sparse MoE's discrete routing mechanism with a differentiable gating function that smoothly mixes tokens. While this smooth gating function successfully mitigates the various training instabilities associated with Sparse MoE, it is unclear whether it induces implicit biases that affect Soft MoE's representation power or potential for expert specialization. We prove that Soft MoE with a single arbitrarily powerful expert cannot represent simple convex functions. This justifies that Soft MoE's success cannot be explained by the traditional viewpoint of many small experts collectively mimicking the representation power of a single large expert, and that multiple experts are actually _necessary_ to achieve good representation power (even for a fixed total parameter count). Continuing along this line of investigation, we introduce a notion of expert specialization for Soft MoE, and while varying the number of experts yet fixing the total parameter count, we consider the following (computationally intractable) task. Given any input, how can we discover the expert subset that is specialized to predict this input's label? We empirically show that when there are many small experts, the architecture is implicitly biased in a fashion that allows us to efficiently approximate the specialized expert subset. Our method can be easily implemented to potentially reduce computation during inference. For example, using our method on ImageNet, one can perform inference using only $1/8$ of the experts and still retain $99$% of the test accuracy of using all experts.

PDF Details

NeurIPS Conference 2025 Conference Paper

What is Your Data Worth to GPT? LLM-Scale Data Valuation with Influence Functions

Sang Choe
Hwijeen Ahn
Juhan Bae
Kewen Zhao
Youngseog Chung
Adithya Pratapa
Willie Neiswanger
Emma Strubell

Large language models (LLMs) are trained on a vast amount of human-written data, but data providers often remain uncredited. In response to this issue, data valuation (or data attribution), which quantifies the contribution or value of each data to the model output, has been discussed as a potential solution. Nevertheless, applying existing data valuation methods to recent LLMs and their vast training datasets has been largely limited by prohibitive compute and memory costs. In this work, we focus on influence functions, a popular gradient-based data valuation method, and significantly improve its scalability with an efficient gradient projection strategy called LoGra that leverages the gradient structure in backpropagation. We then provide a theoretical motivation of gradient projection approaches to influence functions to promote trust in the data valuation process. Lastly, we lower the barrier to implementing data valuation systems by introducing LogIX, a software package that can transform existing training code into data valuation code with minimal effort. In our data valuation experiments, LoGra achieves competitive accuracy against more expensive baselines while showing up to 6, 500x improvement in throughput and 5x reduction in GPU memory usage when applied to Llama3-8B-Instruct and the 1B-token dataset.

PDF Details

ICML Conference 2024 Conference Paper

Sampling-based Multi-dimensional Recalibration

Youngseog Chung
Ian Char
Jeff G. Schneider

Calibration of probabilistic forecasts in the regression setting has been widely studied in the single dimensional case, where the output variables are assumed to be univariate. In many problem settings, however, the output variables are multi-dimensional, and in the presence of dependence across the output dimensions, measuring calibration and performing recalibration for each dimension separately can be both misleading and detrimental. In this work, we focus on representing predictive uncertainties via samples, and propose a recalibration method which accounts for the joint distribution across output dimensions to produce calibrated samples. Based on the concept of highest density regions (HDR), we define the notion of HDR calibration, and show that our recalibration method produces samples which are HDR calibrated. We demonstrate the performance of our method and the quality of the recalibrated samples on a suite of benchmark datasets in multi-dimensional regression, a real-world dataset in modeling plasma dynamics during nuclear fusion reactions, and on a decision-making application in forecasting demand.

Details

UAI Conference 2023 Conference Paper

Parity calibration

Youngseog Chung
Aaron Rumack
Chirag Gupta

In a sequential regression setting, a decision-maker may be primarily concerned with whether the future observation will increase or decrease compared to the current one, rather than the actual value of the future observation. In this context, we introduce the notion of parity calibration, which captures the goal of calibrated forecasting for the increase-decrease (or “parity") event in a timeseries. Parity probabilities can be extracted from a forecasted distribution for the output, but we show that such a strategy leads to theoretical unpredictability and poor practical performance. We then observe that although the original task was regression, parity calibration can be expressed as binary calibration. Drawing on this connection, we use an online binary calibration method to achieve parity calibration. We demonstrate the effectiveness of our approach on real-world case studies in epidemiology, weather forecasting, and model-based control in nuclear fusion.

Details

NeurIPS Conference 2021 Conference Paper

Beyond Pinball Loss: Quantile Methods for Calibrated Uncertainty Quantification

Youngseog Chung
Willie Neiswanger
Ian Char
Jeff Schneider

Among the many ways of quantifying uncertainty in a regression setting, specifying the full quantile function is attractive, as quantiles are amenable to interpretation and evaluation. A model that predicts the true conditional quantiles for each input, at all quantile levels, presents a correct and efficient representation of the underlying uncertainty. To achieve this, many current quantile-based methods focus on optimizing the pinball loss. However, this loss restricts the scope of applicable regression models, limits the ability to target many desirable properties (e. g. calibration, sharpness, centered intervals), and may produce poor conditional quantiles. In this work, we develop new quantile methods that address these shortcomings. In particular, we propose methods that can apply to any class of regression model, select an explicit balance between calibration and sharpness, optimize for calibration of centered intervals, and produce more accurate conditional quantiles. We provide a thorough experimental evaluation of our methods, which includes a high dimensional uncertainty quantification task in nuclear fusion.

PDF Details

NeurIPS Conference 2019 Conference Paper

Offline Contextual Bayesian Optimization

Ian Char
Youngseog Chung
Willie Neiswanger
Kirthevasan Kandasamy
Andrew Nelson
Mark Boyer
Egemen Kolemen
Jeff Schneider

In black-box optimization, an agent repeatedly chooses a configuration to test, so as to find an optimal configuration. In many practical problems of interest, one would like to optimize several systems, or tasks'', simultaneously; however, in most of these scenarios the current task is determined by nature. In this work, we explore the offline'' case in which one is able to bypass nature and choose the next task to evaluate (e. g. via a simulator). Because some tasks may be easier to optimize and others may be more critical, it is crucial to leverage algorithms that not only consider which configurations to try next, but also which tasks to make evaluations for. In this work, we describe a theoretically grounded Bayesian optimization method to tackle this problem. We also demonstrate that if the model of the reward structure does a poor job of capturing variation in difficulty between tasks, then algorithms that actively pick tasks for evaluation may end up doing more harm than good. Following this, we show how our approach can be used for real world applications in science and engineering, including optimizing tokamak controls for nuclear fusion.

PDF Details