Nous utilisons des témoins pour analyser le trafic et l’utilisation de notre site web, afin de personnaliser votre expérience. Vous pouvez désactiver ces technologies à tout moment, mais cela peut restreindre certaines fonctionnalités du site. Consultez notre Politique de protection de la vie privée pour en savoir plus.
Paramètre des cookies
Vous pouvez activer et désactiver les types de cookies que vous souhaitez accepter. Cependant certains choix que vous ferez pourraient affecter les services proposés sur nos sites (ex : suggestions, annonces personnalisées, etc.).
Cookies essentiels
Ces cookies sont nécessaires au fonctionnement du site et ne peuvent être désactivés. (Toujours actif)
Cookies analyse
Acceptez-vous l'utilisation de cookies pour mesurer l'audience de nos sites ?
Multimedia Player
Acceptez-vous l'utilisation de cookies pour afficher et vous permettre de regarder les contenus vidéo hébergés par nos partenaires (YouTube, etc.) ?
Publications
On the Implicit Relation Between Low-Rank Adaptation and Differential Privacy
A significant approach in natural language processing involves large-scale pre-training on general domain data followed by adaptation to spe… (voir plus)cific tasks or domains. As models grow in size, full fine-tuning all parameters becomes increasingly impractical. To address this, some methods for low-rank task adaptation of language models have been proposed, e.g. LoRA and FLoRA. These methods keep the pre-trained model weights fixed and incorporate trainable low-rank decomposition matrices into some layers of the transformer architecture, called adapters. This approach significantly reduces the number of trainable parameters required for downstream tasks compared to full fine-tuning all parameters. In this work, we look at low-rank adaptation from the lens of data privacy. We show theoretically that the low-rank adaptation used in LoRA and FLoRA is equivalent to injecting some random noise into the batch gradients w.r.t the adapter parameters coming from their full fine-tuning, and we quantify the variance of the injected noise. By establishing a Berry-Esseen type bound on the total variation distance between the noise distribution and a Gaussian distribution with the same variance, we show that the dynamics of LoRA and FLoRA are very close to differentially private full fine-tuning the adapters, which suggests that low-rank adaptation implicitly provides privacy w.r.t the fine-tuning data. Finally, using Johnson-Lindenstrauss lemma, we show that when augmented with gradient clipping, low-rank adaptation is almost equivalent to differentially private full fine-tuning adapters with a fixed noise scale.
Neural networks often learn simple explanations that fit the majority of the data while memorizing exceptions that deviate from these explan… (voir plus)ations. This leads to poor generalization when the learned explanations are spurious. In this work, we formalize
Neural networks often learn simple explanations that fit the majority of the data while memorizing exceptions that deviate from these explan… (voir plus)ations. This leads to poor generalization when the learned explanations are spurious. In this work, we formalize
Performative prediction is a framework accounting for the shift in the data distribution induced by the prediction of a model deployed in th… (voir plus)e real world. Ensuring rapid convergence to a stable solution where the data distribution remains the same after the model deployment is crucial, especially in evolving environments. This paper extends the Repeated Risk Minimization (RRM) framework by utilizing historical datasets from previous retraining snapshots, yielding a class of algorithms that we call Affine Risk Minimizers and enabling convergence to a performatively stable point for a broader class of problems. We introduce a new upper bound for methods that use only the final iteration of the dataset and prove for the first time the tightness of both this new bound and the previous existing bounds within the same regime. We also prove that utilizing historical datasets can surpass the lower bound for last iterate RRM, and empirically observe faster convergence to the stable point on various performative prediction benchmarks. We offer at the same time the first lower bound analysis for RRM within the class of Affine Risk Minimizers, quantifying the potential improvements in convergence speed that could be achieved with other variants in our framework.
In many domains, such as healthcare, time-series data is irregularly sampled with varying intervals between observations. This creates chall… (voir plus)enges for classical time-series models that require equally spaced data. To address this, we propose a novel time-series Transformer called **Trajectory Generative Pre-trained Transformer (TrajGPT)**. It introduces a data-dependent decay mechanism that adaptively forgets irrelevant information based on clinical context. By interpreting TrajGPT as ordinary differential equations (ODEs), our approach captures continuous dynamics from sparse and irregular time-series data. Experimental results show that TrajGPT, with its time-specific inference approach, accurately predicts trajectories without requiring task-specific fine-tuning.
In many domains, such as healthcare, time-series data is irregularly sampled with varying intervals between observations. This creates chall… (voir plus)enges for classical time-series models that require equally spaced data. To address this, we propose a novel time-series Transformer called **Trajectory Generative Pre-trained Transformer (TrajGPT)**. It introduces a data-dependent decay mechanism that adaptively forgets irrelevant information based on clinical context. By interpreting TrajGPT as ordinary differential equations (ODEs), our approach captures continuous dynamics from sparse and irregular time-series data. Experimental results show that TrajGPT, with its time-specific inference approach, accurately predicts trajectories without requiring task-specific fine-tuning.
Despite its widespread adoption, Adam's advantage over Stochastic Gradient Descent (SGD) lacks a comprehensive theoretical explanation. This… (voir plus) paper investigates Adam's sensitivity to rotations of the parameter space. We demonstrate that Adam's performance in training transformers degrades under random rotations of the parameter space, indicating a crucial sensitivity to the choice of basis. This reveals that conventional rotation-invariant assumptions are insufficient to capture Adam's advantages theoretically. To better understand the rotation-dependent properties that benefit Adam, we also identify structured rotations that preserve or even enhance its empirical performance. We then examine the rotation-dependent assumptions in the literature, evaluating their adequacy in explaining Adam's behavior across various rotation types. This work highlights the need for new, rotation-dependent theoretical frameworks to fully understand Adam's empirical success in modern machine learning tasks.
Linear mode connectivity (LMC) has become a topic of great interest in recent years. It has been empirically demonstrated that popular deep … (voir plus)learning models trained from different initializations exhibit linear model connectivity up to permutation. Based on this, several approaches for finding a permutation of the model's features or weights have been proposed leading to several popular methods for model merging. These methods enable the simple averaging of two models to create a new high-performance model. However, besides accuracy, the properties of these models and their relationships to the representations of the models they derive from are poorly understood.
In this work, we study the inner mechanisms behind LMC in model merging through the lens of classic feature visualization methods. Focusing on convolutional neural networks (CNNs) we make several observations that shed light on the underlying mechanisms of model merging by permute and average.
Linear mode connectivity (LMC) has become a topic of great interest in recent years. It has been empirically demonstrated that popular deep … (voir plus)learning models trained from different initializations exhibit linear model connectivity up to permutation. Based on this, several approaches for finding a permutation of the model's features or weights have been proposed leading to several popular methods for model merging. These methods enable the simple averaging of two models to create a new high-performance model. However, besides accuracy, the properties of these models and their relationships to the representations of the models they derive from are poorly understood.
In this work, we study the inner mechanisms behind LMC in model merging through the lens of classic feature visualization methods. Focusing on convolutional neural networks (CNNs) we make several observations that shed light on the underlying mechanisms of model merging by permute and average.
The performance of deep neural networks is enhanced by ensemble methods, which average the output of several models. However, this comes at … (voir plus)an increased cost at inference. Weight averaging methods aim at balancing the generalization of ensembling and the inference speed of a single model by averaging the parameters of an ensemble of models. Yet, naive averaging results in poor performance as models converge to different loss basins, and aligning the models to improve the performance of the average is challenging. Alternatively, inspired by distributed training, methods like DART and PAPA have been proposed to train several models in parallel such that they will end up in the same basin, resulting in good averaging accuracy. However, these methods either compromise ensembling accuracy or demand significant communication between models during training. In this paper, we introduce WASH, a novel distributed method for training model ensembles for weight averaging that achieves state-of-the-art image classification accuracy. WASH maintains models within the same basin by randomly shuffling a small percentage of weights during training, resulting in diverse models and lower communication costs compared to standard parameter averaging methods.
Current LLM training positions mathematical reasoning as a core capability. With publicly available sources fully tapped, there is unmet dem… (voir plus)and for diverse and challenging math questions. Relying solely on human experts is both time-consuming and costly, while LLM-generated questions often lack the requisite diversity and difficulty. We present a design framework that combines the strengths of LLMs with a human-in-the-loop approach to generate a diverse array of challenging math questions. We leverage LLM metacognition skills [Didolkar et al., 2024] of a strong LLM to extract core"skills"from existing math datasets. These skills serve as the basis for generating novel and difficult questions by prompting the LLM with random pairs of core skills. The use of two different skills within each question makes finding such questions an"out of distribution"task for both LLMs and humans. Our pipeline employs LLMs to iteratively generate and refine questions and solutions through multiturn prompting. Human annotators then verify and further refine the questions, with their efficiency enhanced via further LLM interactions. Applying this pipeline on skills extracted from the MATH dataset [Hendrycks et al., 2021] resulted in MATH
