FGSM is more stable in adversarially robust transfer learning than PGD.
problem Computational efficiency in adversarially robust transfer learning.
method Revisited use of FGSM in adversarial fine-tuning.
result FGSM is more stable and efficient in adversarial fine-tuning.
FAST improves fast and stable task adaptation in DNNs.
problem Catastrophic forgetting in fine-tuned pretrained models.
method Introducing FAST, an easy-to-implement fine-tuning algorithm.
result FAST learns target tasks faster and retains source knowledge longer.
BERT fine-tuning is unstable due to optimization issues, not forgetting or dataset size.
problem Stability of fine-tuning BERT-based models across different random seeds.
method Analysis of BERT, RoBERTa, and ALBERT fine-tuned on GLUE datasets, identifying optimization difficulties as the cause of instability.
result Fine-tuning instability is due to optimization difficulties leading to vanishing gradients, not forgetting or dataset size.
Self-play fine-tuning improves diffusion models for text-to-image generation.
problem Plateauing performance of diffusion models after data saturation.
method Self-play fine-tuning (SPIN-Diffusion) using competition among model versions.
result Significantly improved model performance and human preference alignment.
Improved RL policies from offline data with relaxed BC constraints.
problem Overestimation bias in offline RL due to lack of interaction with environment.
method Introducing a policy constraint via behavioural cloning (BC) and adjusting the balance between RL and BC.
result Refined policies outperform baseline and match/exceed complex alternatives.
A scalable algorithm for sampling and fine-tuning models using Tilt Matching.
problem Efficient sampling and fine-tuning of generative models.
method Tilt Matching, arising from a dynamical equation, minimizes variance and inherits regularity from stochastic interpolants.
result Empirically verified to be efficient and highly scalable, providing state-of-the-art results.
Paper proposes CLAIR for efficient LLM fine-tuning across clients.
problem Fine-tuning large language models (LLMs) efficiently and collaboratively.
method Federated LoRA fine-tuning with Collaborative Low-rank Alignment and Identifiable Recovery (CLAIR).
result CLAIR achieves better performance and contamination detection compared to local fine-tuning.
Method makes non-interpretable models more intervenable.
problem Making non-interpretable models more understandable and controllable.
method Intervenability formalization and fine-tuning of black-box models.
result Fine-tuned black-box models are more intervenable and often better-calibrated.
Unified framework for training diffusion and flow models to sample from target distributions.
problem Training diffusion and flow models to sample from target distributions defined by exponential tilting.
method Unified framework combining stochastic optimal control and non-equilibrium thermodynamics perspectives.
result Unified bias-variance decompositions and theoretical support for adjoint-based methods.
BEMA reduces bias in EMA, leading to faster convergence and better performance.
problem Stochasticity in language model fine-tuning destabilizes training.
method Bias-Corrected Exponential Moving Average (BEMA) augmentation of EMA.
result BEMA leads to significantly improved convergence rates and final performance.
New method learns optimal variance schedule for diffusion models.
problem Diffusion models' sensitivity to variance schedule.
method Probabilistic conditioning, learning schedule during training.
result Comparable or superior results in super-resolution microscopy and quantitative phase imaging.
Paper resolves bias in ALFT training using generalized alignment games.
problem Systematic bias in estimating logarithmic rewards from small batches.
method Generalized Distributional Alignment Games, U-statistics, minimax polynomial estimators, Variance-Optimal Augmented Polynomial Optimization Program (AQP) Estimator.
result Proves optimal bias and accelerated convergence in ALFT training.
SoftAD improves classification accuracy with less fine-tuning and fewer computational costs.
problem Improving classification accuracy with less fine-tuning and fewer computational costs.
method SoftAD is a softened, pointwise mechanism that downweights borderline points and limits the effects of outliers.
result SoftAD achieves classification accuracy competitive with flooding and SAM, with a smaller loss generalization gap and model norm.
DataInf efficiently approximates data influence in large models, improving transparency and identifying mislabeled data.
problem Efficiently estimating data influence in large-scale models like LoRA-tuned LLMs and diffusion models.
method DataInf uses a closed-form expression to approximate influence scores efficiently.
result DataInf outperforms existing methods in computational and memory efficiency, accurately identifying influential data points.
The stability of money value is an important requisite for a functioning economy, yet it critically depends on the actions of participants in the market themselves. Here we model the value of money as a dynamical variable that results from trading between agents. The basic trading scenario can be recast into an Ising t…
Improves drug properties using a novel LLM and reinforcement learning.
problem Optimizing drug properties while retaining chemical stability.
method Structured Policy Optimization (SPO) for fine-tuning a large language model.
result Enhanced drug properties across multiple target objectives.
New method calibrates LLMs for safety-critical tasks with scalable Bayesian inference.
problem Overconfidence in LLMs after fine-tuning for specific tasks.
method Orthogonalized Low-Rank Adapters (PoLAR) with variational Bayesian inference.
result Scalable and well-calibrated uncertainty estimation for LLMs.
AaSP improves audio self-supervised learning by addressing aliasing issues.
problem Alias issues in audio spectrogram transformers.
method AaSP combines aliasing-aware patch representation, teacher-student masked modeling, cross-attention predictor, and contrastive regularization.
result AaSP learns more stable representations that integrate high-frequency cues.
New measure FTC quantifies how much a ReLU network can fine-tune.
problem Analyzing memorization capacity in fine-tuned neural networks.
method Defined Fine-Tuning Capacity (FTC) for additive fine-tuning of ReLU networks.
result Upper and lower bounds on FTC for 2 and 3-layer ReLU networks.
CyBeR-0 optimizes federated learning with Byzantine resilience and reduced communication costs.
problem Byzantine attacks and communication inefficiency in federated learning.
method Transformed robust aggregation for zero-order optimization under client heterogeneity.
result CyBeR-0 achieves stable performance with minimal communication costs and reduced memory usage.
This paper re-evaluates hyperparameters for fine-tuning pre-trained models.
problem Current hyperparameter settings for fine-tuning are often ad-hoc and fixed.
method Empirical evaluation of learning rate, batch size, and momentum for fine-tuning.
result Optimal hyperparameters are not only dataset-dependent but also sensitive to domain similarity.
FlowLLM uses LLMs and flow matching to efficiently generate novel materials.
problem Challenging material discovery due to vast chemical space.
method Combines LLMs and Riemannian flow matching to design novel crystalline materials.
result Significantly increases generation rate of stable materials and unique crystals.
New method quantifies uncertainty in fine-tuned LLMs using LoRA ensembles.
problem Uncertainty in fine-tuned LLMs and how to trust their predictions.
method Posterior approximations using low-rank adaptation ensembles.
result Unexpected retention of acquired knowledge during fine-tuning in overfitting regime.
Improved code translation by preserving structure with composed fine-tuning.
problem Improving code translation accuracy with unlabeled code outputs.
method Pre-trained denoiser to capture output structure, composed fine-tuning to fine-tune predictor.
result Composed fine-tuning significantly improves generalization over standard fine-tuning.
The paper introduces a Hessian-based method to improve generalization in fine-tuned deep neural networks.
problem Improving generalization in fine-tuned deep neural networks, especially in noisy conditions.
method PAC-Bayesian analysis to identify a Hessian-based distance measure, proving generalization bounds, and developing an algorithm with a generalization error guarantee.
result Hessian-based distance measure correlates well with observed generalization gaps and can match the scale of these gaps in practice.
Fine-tuning LLMs improves capability but harms safety, study finds.
problem Balancing capability and safety in LLM fine-tuning.
method Theoretical framework and numerical experiments for two safety-aware fine-tuning strategies.
result Characterization of fundamental limits of safety-capability trade-off in LLM fine-tuning.
Optimizes sparse fine-tuning for privacy in neural networks.
problem Performance gap between DP-SGD and non-private fine-tuning.
method Optimization-based approach using private gradient information for selecting trainable weights.
result Our selection method leads to better prediction accuracy compared to existing approaches.
Fine-tuning harms in-context learning, but restricting updates to the value matrix improves zero-shot performance.
problem Fine-tuning harms in-context learning, reducing zero-shot performance on unseen tasks.
method Theoretical analysis of linear attention models, identifying conditions for degraded few-shot performance.
result Restricting updates to the value matrix improves zero-shot performance while preserving in-context learning.
Measures consistency of tabular LLM predictions under fine-tuning multiplicity.
problem Conflicting predictions from fine-tuned tabular LLMs.
method Local stability measure in embedding space.
result Probabilistic guarantees on prediction consistency under multiplicity.
The paper develops a theory linking pretraining and fine-tuning in neural networks.
problem Understanding how initialization choices impact feature learning and generalization in neural networks.
method Analytical theory of diagonal linear networks, deriving generalization error as a function of initialization parameters and task statistics.
result Different initialization choices place networks into four fine-tuning regimes with varying abilities to support feature learning and generalization.
New method reduces fine-tuning cost for reused models.
problem Repeating fine-tuning costs with outdated foundation models.
method Portable Reward Tuning (PRT) trains a reward model to maximize the same loss function as fine-tuning.
result PRT achieves comparable accuracy to inference-time tuning with less inference cost.
Compact models match or exceed GPT's performance in financial news sentiment analysis.
problem Improving financial sentiment analysis models without large computational costs.
method Fine-tuning non-generative, small-sized models (FinBERT, FinDRoBERTa) on a novel market score database.
result Fine-tuned models outperform GPT-3.5 and GPT-4 in zero-shot learning for financial news sentiment analysis.
Unsupervised pre-training improves model generalization, but lacks theoretical understanding.
problem Lack of theoretical understanding of unsupervised pre-training's impact on model generalization.
method Introduces a novel theoretical framework to analyze and enhance generalization.
result Enhances understanding of unsupervised pre-training and fine-tuning, proposing a new regularization method.
LP-FT improves personalized model training in FL by balancing generalization and personalization.
problem Federated Learning struggles with balancing global generalization and local personalization due to non-identical data distributions.
method Adapting Linear Probing followed by full Fine-Tuning (LP-FT) to the FL setting.
result LP-FT outperforms standard fine-tuning in balancing personalization and generalization across various datasets and PFT variants.
UBM transfers bias mitigation from upstream to downstream tasks efficiently.
problem Bias in fine-tuned language models across various tasks.
method Apply bias mitigation to an upstream model, then fine-tune a downstream model on this mitigated model.
result UBM effects transfer to new downstream tasks, creating less biased models.
Improved fine-tuning with regularization and robustness for noisy labels.
problem Fine-tuning pre-trained models on small datasets can lead to overfitting and memorization.
method PAC-Bayes generalization bound analysis, layer-wise regularization, self-label-correction, label-reweighting.
result Improves performance by 1.76% on average for image classification tasks and 0.75% for few-shot classification.
Paper improves bike-sharing demand prediction by adapting to changing patterns.
problem Improving bike-sharing demand prediction under temporal domain shifts.
method Gen-ROTDA, a robust optimal transport-guided residual domain adaptation framework.
result Gen-ROTDA achieves the lowest MAE and is the best OT-family method on average.
Simplified trust region method reduces representation change during fine-tuning.
problem Stability and representational collapse in fine-tuning pre-trained models.
method Replaces adversarial objectives with parametric noise in trust region theory.
result Matches or exceeds previous trust region methods in performance and speed.
Adjoint Matching improves flow and diffusion models with reward fine-tuning.
problem Improving generative models with reward fine-tuning.
method Casting reward fine-tuning as stochastic optimal control (SOC) and enforcing a specific noise schedule.
result Adjoint Matching outperforms existing SOC algorithms.
Fine-tunes LLMs to correct bias in predictions.
problem LLMs exhibit bias in predictions from data.
method Supervised fine-tuning with Low-Rank Adaptation (LoRA).
result Fine-tuning corrects bias in both controlled and real-world settings.
Transfer learning, which allows a source task to affect the inductive bias of the target task, is widely used in computer vision. The typical way of conducting transfer learning with deep neural networks is to fine-tune a model pre-trained on the source task using data from the target task. In this paper, we propose an…
Fine-tuning large language models requires minimal data, making them efficient.
problem Achieving state-of-the-art performance with large language models.
method Using BERT as an example, fine-tuning only the most critical layers of the pre-trained model.
result Fine-tuned models are close in parameter space to the pre-trained model, with many good solutions found in sparsified versions.
Fine-tuning improves meta-learning by leveraging shared representations.
problem Meta-learning's challenge in rapidly learning new tasks.
method Theoretical framework and risk bounds on gradient descent fine-tuning.
result Fine-tuning-based methods can provably leverage shared structure.
New method enhances model fine-tuning with minimal data.
problem Improving model performance on new tasks with limited data.
method Introducing α-LoRA, a reparameterization method for fine-tuning. result Enhanced generalization ability of fine-tuned models.
Transformers fine-tuned on synthetic data boost tabular data classification performance.
problem Improving tabular data classification accuracy.
method Fine-tuning ICL-transformers on synthetic datasets with complex decision boundaries.
result Fine-tuned ICL-transformers outperform regular neural networks on real-world datasets.
A new method constrains deep networks during fine-tuning to improve generalization.
problem Improving generalization of fine-tuned deep networks.
method A neural network generalisation bound based on distance from initial weights constrains the hypothesis class to a small sphere.
result Empirical evaluation shows superior generalization performance compared to existing methods.
Fine-tuning with pre-training data improves performance.
problem Limited training data for tasks.
method Theoretical analysis of excess risk bound and selection of pre-training data subset.
result Improvement in generalization performance with pre-training data.
New method fine-tunes discrete diffusion models for RLHF tasks.
problem Fine-tuning discrete diffusion models with policy gradient methods is challenging.
method Proposed SEPO algorithm for efficient fine-tuning over non-differentiable rewards.
result Numerical experiments show scalability and efficiency of SEPO.