Optimal Completion Distillation improves speech recognition models efficiently.
problem Improving sequence to sequence models for speech recognition.
method Optimal suffix selection using dynamic programming and target distribution.
result Achieves state-of-the-art performance on speech datasets.
Labels distilled from images improve model training efficiency and flexibility.
problem Creating synthetic labels for a small set of real images to train models effectively.
method Introduce a more robust and flexible meta-learning algorithm for distillation and an effective first-order strategy based on convex optimization layers.
result Label distillation leads to improved results and greater flexibility in neural architectures.
A framework preserves uncertainty in ensemble distillation.
problem Preserving uncertainty decomposition in ensemble distillation.
method General framework for distilling both regression and classification ensembles, preserving natural uncertainty decomposition.
result Framework maintains decomposition of predictive uncertainty.
Self-distillation optimally improves model performance in spiked covariance models.
problem Improving model performance in spiked covariance models.
method Developed spectral shrinkage estimators and analyzed self-distillation.
result Self-distillation achieves optimal performance among spectral shrinkage estimators for spiked covariance matrices.
Optimal quantization improves dataset distillation for faster training.
problem Efficiently train models with synthetic data.
method Reformulate disentangled methods as optimal quantization problems.
result Better performance and generalization on ImageNet-1K and subsets.
Estimates model performance from compute budget for distillation.
problem Risk mitigation in large-scale distillation.
method Distillation scaling law based on compute budget allocation.
result Maximizes student performance with compute-optimal allocation.
A modular framework for knowledge distillation simplifies experiments and reproducibility.
problem Difficulty in reproducing knowledge distillation studies due to lack of generalized frameworks.
method A configuration-driven PyTorch framework for knowledge distillation studies.
result Demonstrates efficient training strategies and various knowledge distillation methods.
A new method distills datasets more efficiently and effectively.
problem Achieving competitive performance on test data with a small synthetic dataset.
method Tackles dataset distillation as a bilevel optimization problem, introduces RaT-BPTT to stabilize gradients and speed up optimization.
result Establishes new state-of-the-art performance across various benchmarks.
New methods distill dynamical system equations from data.
problem Discovering governing equations of dynamical systems from data.
method Sparse regression, LASSO, dual LASSO optimization, STRidge algorithm.
result Improved accuracy and stability in learning dynamical system equations.
Study on ensemble, distillation, and self-distillation in deep learning models.
problem Improving test accuracy in deep learning models using ensemble and distillation methods.
method Formal study of ensemble and distillation, considering multi-view data structure.
result Proven that ensemble and distillation can improve test accuracy in deep learning models, and the superior performance can be distilled into a single model.
Current approaches for Knowledge Distillation (KD) either directly use training data or sample from the training data distribution. In this paper, we demonstrate effectiveness of 'mismatched' unlabeled stimulus to perform KD for image classification networks. For illustration, we consider scenarios where this is a comp…
Optimal self-distillation improves generative models' velocity risk and mode recovery.
problem Improving generative models' velocity risk and mode recovery.
method Proved optimal self-distillation for rectified flow via linear probing, derived mixing coefficient, and provided validation tuning.
result Optimal self-distillation improves velocity risk and mode recovery.
DGKIP extends KIP for dataset distillation without bi-level optimization.
problem Efficiently distill datasets for various loss functions.
method Leverages duality theory to avoid bi-level optimization.
result DGKIP supports a wider range of loss functions.
The paper explains knowledge distillation by analyzing visual concepts in DNNs.
problem Understanding how knowledge distillation affects the learning of visual concepts in deep neural networks.
method The paper proposes three hypotheses and designs mathematical metrics to evaluate feature representations of DNNs.
result The hypotheses were verified through experiments on various DNNs.
Distillation speeds up classifier training and provides insights into its success.
problem Empirical success of knowledge distillation without theoretical explanation.
method Study of linear and deep linear classifiers, proving a generalization bound.
result Three key factors for distillation success: data geometry, optimization bias, strong monotonicity.
CAKD framework optimizes knowledge transfer by focusing on influential components of distillation.
problem Balancing and optimizing knowledge transfer in distillation models.
method Decouple KL divergence into BCD, SCD, and WCD; prioritize influential components.
result CAKD framework consistently outperforms baseline across diverse models and datasets.
Distilled models often fail to match teacher models, despite improving generalization.
problem The discrepancy between teacher and student predictive distributions remains large.
method Investigated the optimization difficulties and dataset details affecting student performance.
result Optimizing for matching the teacher does not always lead to better generalization.
Improved generalization with iterative self-distillation using weighted ground-truth targets.
problem Improving generalization accuracy in neural networks.
method Iterative kernel regression with weighted ground-truth targets and ℓ 2 \ell_2 ℓ 2 regularization. result Closed-form solution for optimal weighting parameter and efficient estimation.
TL-ANDI distills context from source data to improve transfer learning for TFMs.
problem Limited transfer learning due to context-size constraints and distribution shifts.
method TL-ANDI uses posterior-aware distillation to construct a compact source context and locally distills labels.
result Improves transfer performance by addressing context-size and distribution shifts.
This paper investigates teacher hacking during language model distillation and proposes methods to mitigate it.
problem Teacher hacking during language model distillation, leading to suboptimal performance.
method A controlled experimental setup involving an oracle LM, teacher LM, and student LM, using fixed offline or online data generation techniques.
result Data diversity is the key factor in preventing teacher hacking during distillation.
New algorithm improves dataset distillation with 108% improvement on ImageNet.
problem Improving dataset distillation performance.
method Reparameterization and convexification of implicit gradients (RCIG).
result Establishes new state-of-the-art on various dataset distillation tasks.
PLD distills knowledge using choice-theoretic Plackett-Luce model.
problem Model compression and knowledge transfer between large and small networks.
method PLD uses a weighted list-wise ranking loss based on the Plackett-Luce model.
result PLD achieves consistent gains across diverse architectures and distillation methods.
RID framework quantifies and regularizes task-relevant knowledge in distillation.
problem Distilling irrelevant information can hinder student model performance.
method Partial Information Decomposition to quantify and regularize task-relevant knowledge.
result RID framework leads to more resilient distillation under nuisance teachers.
New MARL method combines agent knowledge to reduce complexity.
problem Curse of dimensionality in multiagent reinforcement learning.
method Decomposes multiagent problem into multi-task problem, uses distillation and value-matching.
result Outperforms policy distillation alone and improves learning in both discrete and continuous action spaces.
A new distillation method transfers channel information from teacher to student.
problem Transfer knowledge from teacher to student with fewer parameters and calculations.
method Channel Distillation (CD) and Guided Knowledge Distillation (GKD) with loss decay.
result Achieved 27.68% top-1 error on ImageNet with ResNet18, outperforming state-of-the-art methods.
This paper improves speech recognition by distilling knowledge from acoustic models.
problem Improving speech recognition accuracy using ensemble models.
method Proposes multi-teacher distillation strategies for joint CTC-attention end-to-end ASR systems, integrating error rate metric for optimization.
result Reports state-of-the-art error rates on various datasets and languages.
Knowledge distillation improves model accuracy by mimicking teacher model probabilities.
problem Improving model accuracy through model compression.
method Casting knowledge distillation as a semiparametric inference problem, deriving new guarantees, and developing enhancements.
result Enhancements improve student performance by mitigating teacher overfitting and underfitting.
A new KD method distills dataset-based knowledge using MHA.
problem Distilling knowledge from large teacher networks to small student networks.
method Graph-based knowledge distillation by multi-head attention network.
result The method improves SN performance by 7.05% on CIFAR100.
New method distills cloud models into edge-friendly ones.
problem Cloud-to-edge model compression with limited data exchange.
method Two-step workflow of deprivatization and distillation.
result Outperforms previous state-of-the-art approaches on various benchmarks.
Hybrid approach combines Markowitz's theory with reinforcement learning for optimal portfolio management.
problem Optimizing investment portfolios while balancing returns and risks.
method Knowledge distillation for training reinforcement learning agents.
result Achieves highest yield and Sharpe ratio of 2.03, ensuring top profitability with low risk.
One of the key differences between the learning mechanism of humans and Artificial Neural Networks (ANNs) is the ability of humans to learn one task at a time. ANNs, on the other hand, can only learn multiple tasks simultaneously. Any attempts at learning new tasks incrementally cause them to completely forget about pr…
EM Distillation simplifies diffusion models to one-step generators.
problem Efficient sampling from complex diffusion models with minimal loss of quality.
method EM Distillation, a maximum likelihood approach based on Expectation-Maximization.
result EM Distillation outperforms existing one-step generative methods in FID scores.
FairDTD improves fairness in GNNs by distilling dual teacher knowledge, balancing utility and bias.
problem Bias in GNN predictions due to sensitive attributes.
method Dual-Teacher Distillation with a causal graph model, feature and structure teachers, and graph-level distillation.
result Achieves optimal fairness while preserving high model utility.
A new algorithm improves federated learning by combining knowledge distillation and weighted combination loss.
problem Non-IID client data in federated learning leads to model drift and poor generalization.
method pFedKD-WCL integrates knowledge distillation with bi-level optimization to address non-IID challenges.
result pFedKD-WCL outperforms state-of-the-art algorithms in accuracy and convergence speed.
The paper establishes theoretical foundations for low-rank knowledge distillation in LLMs.
problem Understanding the theoretical underpinnings of low-rank knowledge distillation in LLMs.
method Theoretical framework for low-rank knowledge distillation, including convergence rates and generalization bounds.
result Theoretical analysis reveals optimal rank r ∗ = O ( n ) r^* = O(\sqrt{n}) r ∗ = O ( n ) for minimizing generalization error. Recent variants improve knowledge distillation performance.
problem Improving the performance of knowledge distillation.
method Introducing additional components or changing the learning process.
result These variants have shown promising results.
Paper proposes a novel policy distillation method for better order execution in noisy markets.
problem Effective order execution in noisy and imperfect market conditions.
method Policy distillation method to guide reinforcement learning towards optimal trading strategies.
result Significant improvements over various baselines in order execution.
A new method for distilling predictions from a teacher model to a student model without original training data.
problem Training without original labeled data.
method Prediction-only distillation scheme for linear and logistic regression.
result Prediction mixing can outperform both the teacher and pure-distilled models.
FED distills ensemble predictions efficiently, improving accuracy and uncertainty.
problem Efficiently distilling ensemble predictions from limited data.
method Proposes Functional Ensemble Distillation (FED) using mixup augmentation.
result Significantly boosts performance in accuracy and uncertainty estimation.
Survey examines distillation methods for large language models.
problem Efficiently compress large language models while preserving their capabilities.
method Knowledge Distillation and Dataset Distillation techniques.
result Integrating KD and DD can produce more effective and scalable compression strategies.
Bad models can teach well by replicating noise.
problem Overparameterized models can replicate noise in training data.
method Knowledge distillation from noisy samplers.
result Distillation from samplers approximates Bayes optimal classifier.
Paper analyzes dataset distillation for efficient encoding of task-relevant information.
problem Efficiently encoding task-relevant information from gradient-based learning of non-linear tasks.
method Theoretical analysis of dataset distillation applied to two-layer neural networks with gradient-based training.
result Low-dimensional structure of the problem is efficiently encoded into distilled data, reproducing a model with high generalization ability.
Efficiently distills pretrained text-to-image models without real data, improving FID and CLIP scores.
problem Slow iterative refinement process of diffusion-based text-to-image models.
method Guided Score identity Distillation with Long and Short Classifier-Free Guidance.
result Achieves state-of-the-art FID performance with competitive CLIP score.
Develops efficient algorithm for distilling supervised and offline RL datasets.
problem Creating synthetic datasets for supervised and offline RL models to match training data performance.
method An efficient algorithm based on matching losses without model training, using randomly sampled regressors.
result Synthetic datasets derived with i l d e O ( d 2 ) ilde{O}(d^2) i l d e O ( d 2 ) sampled regressors match MSE loss of bounded linear models on training data. Few-step distillation improves T2I models without real images or CFG trade-offs.
problem Challenges in accelerating T2I models with high-resolution and CFG.
method Score identity distillation (SiD) for few-step generation, with adversarial loss and new guidance strategies.
result State-of-the-art performance on SDXL at 1024x1024 resolution, robust to real images absence.
Efficiently distills white-box adversarial attacks into black-box models.
problem Generating efficient adversarial examples for robustness.
method Train a model to emulate white-box attack behavior and distill it into a more efficient black-box model.
result Reduces adversarial example generation time by 19x-39x and transfers to black-box settings.
DONNA rapidly finds optimal neural networks across diverse spaces.
problem Efficient scaling and handling of diverse architectural search-spaces in NAS.
method Three-phase pipeline: accuracy predictor, rapid evolutionary search, and optimal model finetuning.
result 100x faster than MNasNet in finding state-of-the-art architectures on-device.
A new method for exploration in reinforcement learning improves performance on Atari games.
problem Improving exploration in reinforcement learning algorithms, especially for complex games.
method Random Network Distillation (RND) bonus combined with flexible reward combination.
result Significant progress on hard exploration Atari games, including Montezuma's Revenge.