Search Results for author:
Found 25 papers, 10 papers with code
Flavors of Margin: Implicit Bias of Steepest Descent in Homogeneous Neural Networks
We study the implicit bias of the general family of steepest descent algorithms, which includes gradient descent, sign descent and coordinate descent, in deep homogeneous neural networks.
On the Geometry of Regularization in Adversarial Training: High-Dimensional Asymptotics and Generalization Bounds
Indeed, controlling the complexity of the model class is particularly important when data is scarce, noisy or contaminated, as it translates a statistical belief on the underlying structure of the data.
Emergent properties with repeated examples
We study the performance of transformers as a function of the number of repetitions of training examples with algorithmically generated datasets.
Strong Model Collapse
Within the scaling laws paradigm, which underpins the training of large neural networks like ChatGPT and Llama, we consider a supervised regression setting and establish the existance of a strong form of the model collapse phenomenon, a critical performance degradation due to synthetic data in the training corpus.
Beyond Model Collapse: Scaling Up with Synthesized Data Requires Verification
Large Language Models (LLM) are increasingly trained on data generated by other LLM, either because generated text and images become part of the pre-training corpus, or because synthetized data is used as a replacement for expensive human-annotation.
The Price of Implicit Bias in Adversarially Robust Generalization
We study the implicit bias of optimization in robust empirical risk minimization (robust ERM) and its connection with robust generalization.
Iteration Head: A Mechanistic Study of Chain-of-Thought
Chain-of-Thought (CoT) reasoning is known to improve Large Language Models both empirically and in terms of theoretical approximation power.
Attacking Bayes: On the Adversarial Robustness of Bayesian Neural Networks
Adversarial examples have been shown to cause neural networks to fail on a wide range of vision and language tasks, but recent work has claimed that Bayesian neural networks (BNNs) are inherently robust to adversarial perturbations.
DRoP: Distributionally Robust Pruning
In the era of exceptionally data-hungry models, careful selection of the training data is essential to mitigate the extensive costs of deep learning.
Mind the GAP: Improving Robustness to Subpopulation Shifts with Group-Aware Priors
Machine learning models often perform poorly under subpopulation shifts in the data distribution.
Model Collapse Demystified: The Case of Regression
In the era of proliferation of large language and image generation models, the phenomenon of "model collapse" refers to the situation whereby as a model is trained recursively on data generated from previous generations of itself over time, its performance degrades until the model eventually becomes completely useless, i. e the model collapses.
A Tale of Tails: Model Collapse as a Change of Scaling Laws
We discover a wide range of decay phenomena, analyzing loss of scaling, shifted scaling with number of generations, the ''un-learning" of skills, and grokking when mixing human and synthesized data.
Deconstructing the Goldilocks Zone of Neural Network Initialization
The second-order properties of the training loss have a massive impact on the optimization dynamics of deep learning models.
Discovering Galaxy Features via Dataset Distillation
In many applications, Neural Nets (NNs) have classification performance on par or even exceeding human capacity.
On the Robustness of Neural Collapse and the Neural Collapse of Robustness
We further analyze the geometry of networks that are optimized to be robust against adversarial perturbations of the input, and find that Neural Collapse is a pervasive phenomenon in these cases as well, with clean and perturbed representations forming aligned simplices, and giving rise to a robust simple nearest-neighbor classifier.
Kernels, Data & Physics
Lecture notes from the course given by Professor Julia Kempe at the summer school "Statistical physics of Machine Learning" in Les Houches.
Wavelets Beat Monkeys at Adversarial Robustness
2) Replacing the front-end VOneBlock by an off-the-shelf parameter-free Scatternet followed by simple uniform Gaussian noise can achieve much more substantial adversarial robustness without adversarial training.
What Can the Neural Tangent Kernel Tell Us About Adversarial Robustness?
The adversarial vulnerability of neural nets, and subsequent techniques to create robust models have attracted significant attention; yet we still lack a full understanding of this phenomenon.
ImpressLearn: Continual Learning via Combined Task Impressions
Starting from existing work on network masking (Wortsman et al., 2020), we show that simply learning a linear combination of a small number of task-specific supermasks (impressions) on a randomly initialized backbone network is sufficient to both retain accuracy on previously learned tasks, as well as achieve high accuracy on unseen tasks.
Can we achieve robustness from data alone?
In parallel, we revisit prior work that also focused on the problem of data optimization for robust classification \citep{Ily+19}, and show that being robust to adversarial attacks after standard (gradient descent) training on a suitable dataset is more challenging than previously thought.
The NTK Adversary: An Approach to Adversarial Attacks without any Model Access
In particular, in the regime where the Neural Tangent Kernel theory holds, we derive a simple, but powerful strategy for attacking models, which in contrast to prior work, does not require any access to the model under attack, or any trained replica of it for that matter.
Connectivity Matters: Neural Network Pruning Through the Lens of Effective Sparsity
Neural network pruning is a fruitful area of research with surging interest in high sparsity regimes.
Quantum random walks - an introductory overview
This article aims to provide an introductory survey on quantum random walks.
Quantum Physics Data Structures and Algorithms
Quantum Walks On Graphs
We set the ground for a theory of quantum walks on graphs- the generalization of random walks on finite graphs to the quantum world.
Quantum Physics
Universal simulation of Markovian quantum dynamics
Although the conditions for performing arbitrary unitary operations to simulate the dynamics of a closed quantum system are well understood, the same is not true of the more general class of quantum operations (also known as superoperators) corresponding to the dynamics of open quantum systems.
Quantum Physics
