On the Generalization of Knowledge Distillation: An Information-Theoretic View

Knowledge Distillation (KD) is a central paradigm for transferring knowledge from a large teacher network to a typically smaller student model, often by leveraging soft probabilistic outputs. While KD has shown strong empirical success in numerous applications, its theoretical underpinnings remain only partially understood. In this work, we adopt a Bayesian perspective on KD to rigorously analyze the convergence behavior of students trained with Stochastic Gradient Descent (SGD). We study two regimes: $(i)$ when the teacher provides the exact Bayes Class Probabilities (BCPs); and $(ii)$ supervision with noisy approximations of the BCPs. Our analysis shows that learning from BCPs yields variance reduction and removes neighborhood terms in the convergence bounds compared to one-hot supervision. We further characterize how the level of noise affects generalization and accuracy. Motivated by these insights, we advocate the use of Bayesian deep learning models, which typically provide improved estimates of the BCPs, as teachers in KD. Consistent with our analysis, we experimentally demonstrate that students distilled from Bayesian teachers not only achieve higher accuracies (up to +4.27%), but also exhibit more stable convergence (up to 30% less noise), compared to students distilled from deterministic teachers.

This position paper argues that knowledge distillation must account for what it loses: student models should be judged not only by retained task scores, but by whether they preserve the teacher capabilities that make those scores reliable. This matters because distillation is increasingly used to turn large teacher models into deployable students, yet headline metrics can obscure losses in the capabilities that make teacher behavior reliable. Conceptually, we show that current evaluation often assumes retained task scores imply retained teacher capabilities. Reframing distillation as a lossy projection exposes this flaw: students may match selected teacher observables without preserving the capabilities that make them reliable. We then synthesize existing evidence into a taxonomy of off-metric distillation losses, showing that such losses are concrete, recurring, and measurable, yet often unaccounted for when studies report what students retain rather than what they lose. To make the position actionable, we propose scenario-specific preservation targets and a Distillation Loss Statement that reports what was preserved, what was lost, and why the remaining losses are acceptable. The goal is not lossless distillation, but accountable distillation.

Knowledge distillation (KD) transfers knowledge from a high-capacity teacher to a compact student by matching their predictive distributions, with temperature scaling serving as a central mechanism for smoothing teacher predictions and exposing informative "dark knowledge" beyond the hard label. However, the standard fixed-temperature design is inherently sample-agnostic. Since samples differ in logit scale and learning difficulty, a single global temperature produces teacher soft labels with highly inconsistent entropy: some predictions remain overly sharp and provide limited inter-class information, whereas others become over-smoothed and lose class-discriminative information. Moreover, sharing the same temperature between teacher and student further imposes rigid logit-scale alignment despite their capacity mismatch. To address these limitations, we propose CIST (Consistently Informative Soft-label Temperature), which assigns separate sample-wise adaptive temperatures to the teacher and student. This design produces consistently informative teacher soft labels while relaxing rigid teacher--student logit-scale matching. It also reweights the distillation objective according to teacher confidence and student learning difficulty. Theoretically, we show that teacher-label entropy is largely governed by the ratio between the maximum teacher logit and the temperature, providing a principled basis for adaptive smoothing. Empirically, CIST mitigates the inconsistency induced by fixed temperature, and experiments on both vision and language distillation tasks show consistent improvements over standard KD and strong baselines with negligible computational overhead.