Searcharxiv⌕ Search

arXiv subjects

Sanghwa Kim

Publications and source records attributed to Sanghwa Kim.

7 recordsLinked to original sources

Instance-Optimal Estimation with Multiple LLM Judges on a Budget

Evaluating large language models increasingly relies on LLM-as-a-judge protocols, but such evaluations remain costly: different judges have different prices and reliabilities, and the difficulty of each prompt-response pair can vary substantially. This raises a basic allocation question: under a fixed budget, how should one distribute evaluation queries across heterogeneous judges and instances to obtain the most accurate score estimates? We formalize this question as budgeted heteroskedastic multi-judge estimation under independent, unbiased score observations. Given $K$ prompt-response pairs and $J$ judges with known costs but unknown query-judge variances, our goal is to estimate the bounded score vector while minimizing an $\ell_p$-error. Our first contribution is to analyze the inverse-variance weighted estimator (IVWE) and to derive the oracle allocation that minimizes its leading error bound. Since this allocation depends on the unknown variances, we then address the unknown-variance setting by proposing EST-IVWE, an adaptive algorithm that constructs and uses optimistic variance estimates to stabilize the empirical allocation. We prove that EST-IVWE matches the oracle IVWE rate up to lower-order terms in the budget. Our second and central theoretical contribution is a local minimax lower bound matching the leading allocation-dependent rate, establishing asymptotic instance-optimality up to logarithmic factors. An Assouad-type construction based on local, variance-preserving perturbations yields this bound both in expectation and with constant probability. A complementary Fano-type change-of-measure argument captures the logarithmic dependence on the confidence level with a different (suboptimal) allocation geometry. Finally, we numerically validate our approach on synthetic data and resampled HelpSteer2 evaluations, demonstrating improvements over naïve uniform allocation.

cs.LG↗

A Jointly Efficient and Near-Optimal Algorithm for Heteroskedastic Generalized Linear Bandits with Adversarial Corruptions

We consider heteroskedastic generalized linear bandits (GLBs) with adversarial corruptions and propose \texttt{HCW-GLB-OMD}, a simple algorithm that combines an online mirror descent (OMD)-based estimator with Hessian-based confidence weights. Although both components are well studied, establishing guarantees for the combined algorithm requires a nontrivial analysis. We establish a corruption-robust confidence sequence using technical tools not required in prior analyses, including a weighted likelihood supermartingale and a self-bounding argument. For the regret analysis, we derive a new Hessian potential lemma to handle the interaction between adversarial corruption and adaptive confidence weighting. For self-concordant GLMs, we prove a high-probability regret bound of $\widetilde{\mathcal{O}}\bigl( d \sqrt{\sum_t g(τ_t) \dotμ_{t,\star}} + d^2 g_{\max} κ+ d(1+κ)(C\vee1) \bigr)$, where $\dotμ_{t,\star}$ is the slope of $μ$ at the optimal arm at time $t$, $g(τ_t)$ is the observed dispersion, $g_{\max}=\max_t g(τ_t)$, $κ$ is the worst-case inverse slope of $μ$, and $C$ is the corruption budget. The algorithm attains this bound with one OMD update per round and $\mathcal{O}(d^2)$ storage. We complement this guarantee with matching lower bounds for the leading $\sqrt{T}$ term and, up to $κ$, the $dC$ corruption term.

cs.LG↗

Beyond Second-Order Information: Paid Logistic Regression with Noisy Features

We consider online binary prediction with paid stochastic features, where the learner can spend resources to obtain better observations of the underlying features. This setting is motivated by applications such as medical testing, where additional cost can provide more precise measurements of patient's features for predicting a binary outcome. At each round, a latent feature is drawn i.i.d., the response is generated through a logistic model, and the learner chooses how much to pay before observing a noisy version of the feature. The goal of learner is to jointly control prediction loss and acquisition cost. In contrast to the former result on the online linear regression with paid features, covariance information alone is no longer sufficient: two noise distributions with the same covariance may induce different optimal logistic losses, and lower variance can even lead to higher loss. Under a structural ordering in which larger payments yield better observations by removing independent noise, we obtain $\widetilde O(\sqrt{T})$ regret when the noise structure is known and $\widetilde O(T^{2/3})$ regret when it is unknown, with matching lower bounds up to logarithmic factors.

stat.ML↗

Pointwise or Pairwise: When Do Pairwise Losses Help Reward Learning, Provably?

Pairwise losses are increasingly used for reward learning even when pointwise rewards are observed, with mixed empirical results. When and why do pairwise losses outperform pointwise losses? We study this question in a grouped offline contextual-bandit setting allowing multiple actions per context, capturing many reward learning scenarios. We compare Value Regression (VR), which regresses observed rewards pointwise, with Value Difference Regression (VDR), which regresses reward differences between a pair of actions sampled under the same context. We consider a semiparametric model where the mean reward is the sum of a learnable action-dependent component and an arbitrary context-dependent yet action-independent nuisance, capturing context-specific disturbances. Using a unified localized analysis, we prove finite-sample regression guarantees for finite and linear function classes and translate them into offline-regret bounds. For finite classes, VDR eliminates the misspecification term in the VR bound and improves a reward-scale-dependent error term by averaging over actions within each context, a benefit absent from the corresponding VR term. For linear classes, neither method uniformly dominates: within-context differencing removes nuisance-induced bias but may increase estimation variance relative to using absolute rewards when the misspecification is sufficiently low. This yields a feature geometry-dependent bias-variance tradeoff, which we corroborate with numerical experiments.

cs.LG↗

On the Optimality of Tracking Fisher Information in Adaptive Testing with Stochastic Binary Responses

We study the problem of estimating a continuous ability parameter from sequential binary responses by actively asking questions with varying difficulties, a setting that arises naturally in adaptive testing and online preference learning. Our goal is to certify that the estimate lies within a desired margin of error, using as few queries as possible. We propose a simple algorithm that adaptively selects questions to maximize Fisher information and updates the estimate using a method-of-moments approach, paired with a novel test statistic to decide when the estimate is accurate enough. We prove that this Fisher-tracking strategy achieves optimal performance in both fixed-confidence and fixed-budget regimes, which are commonly invested in the best-arm identification literature. Our analysis overcomes a key technical challenge in the fixed-budget setting -- handling the dependence between the evolving estimate and the query distribution -- by exploiting a structural symmetry in the model and combining large deviation tools with Ville's inequality. Our results provide rigorous theoretical support for simple and efficient adaptive testing procedures.

stat.ML↗

Pre-Storage Reasoning for Episodic Memory: Shifting Inference Burden to Memory for Personalized Dialogue

Effective long-term memory in conversational AI requires synthesizing information across multiple sessions. However, current systems place excessive reasoning burden on response generation, making performance significantly dependent on model sizes. We introduce PREMem (Pre-storage Reasoning for Episodic Memory), a novel approach that shifts complex reasoning processes from inference to memory construction. PREMem extracts fine-grained memory fragments categorized into factual, experiential, and subjective information; it then establishes explicit relationships between memory items across sessions, capturing evolution patterns like extensions, transformations, and implications. By performing this reasoning during pre-storage rather than when generating a response, PREMem creates enriched representations while reducing computational demands during interactions. Experiments show significant performance improvements across all model sizes, with smaller models achieving results comparable to much larger baselines while maintaining effectiveness even with constrained token budgets. Code and dataset are available at https://github.com/sangyeop-kim/PREMem.

cs.CL↗

Emergence of a Metal-Insulator Transition and High Temperature Charge Density Waves in VSe2 at the Monolayer Limit

Emergent phenomena driven by electronic reconstructions in oxide heterostructures have been intensively discussed. However, the role of these phenomena in shaping the electronic properties in van der Waals heterointerfaces has hitherto not been established. By reducing the material thickness and forming a heterointerface, we find two types of charge-ordering transitions in monolayer VSe2 on graphene substrates. Angle-resolved photoemission spectroscopy (ARPES) uncovers that Fermi-surface nesting becomes perfect in ML VSe2. Renormalization group analysis confirms that imperfect nesting in three dimensions universally flows into perfect nesting in two dimensions. As a result, the charge density wave transition temperature is dramatically enhanced to a value of 350 K compared to the 105 K in bulk VSe2. More interestingly, ARPES and scanning tunneling microscopy measurements confirm an unexpected metal-insulator transition at 135 K, driven by lattice distortions. The heterointerface plays an important role in driving this novel metal-insulator transition in the family of monolayered transition metal dichalcogenides.

cond-mat.str-el↗