Search Results for author:
Found 60 papers, 28 papers with code
Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space
We address this research gap and propose the embedding space attack, which directly attacks the continuous embedding representation of input tokens.
Iterated Denoising Energy Matching for Sampling from Boltzmann Densities
Efficiently generating statistically independent samples from an unnormalized probability distribution, such as equilibrium samples of many-body systems, is a foundational problem in science.
In-Context Learning Can Re-learn Forbidden Tasks
Specifically, we investigate whether in-context learning (ICL) can be used to re-learn forbidden tasks despite the explicit fine-tuning of the model to refuse them.
Adversarial Attacks and Defenses in Large Language Models: Old and New Threats
Here, one major impediment has been the overestimation of the robustness of new defense approaches due to faulty defense evaluations.
Proving Linear Mode Connectivity of Neural Networks via Optimal Transport
The energy landscape of high-dimensional non-convex optimization problems is crucial to understanding the effectiveness of modern deep neural network architectures.
Expected flow networks in stochastic environments and two-player zero-sum games
Generative flow networks (GFlowNets) are sequential sampling models trained to match a given distribution.
High-Probability Convergence for Composite and Distributed Stochastic Minimization and Variational Inequalities with Heavy-Tailed Noise
High-probability analysis of stochastic first-order optimization methods under mild assumptions on the noise has been gaining a lot of attention in recent years.
On the Stability of Iterative Retraining of Generative Models on their own Data
In this paper, we develop a framework to rigorously study the impact of training generative models on mixed datasets -- from classical training on real data to self-consuming generative models trained on purely synthetic data.
AI4GCC -- Track 3: Consumption and the Challenges of Multi-Agent RL
The AI4GCC competition presents a bold step forward in the direction of integrating machine learning with traditional economic policy analysis.
Omega: Optimistic EMA Gradients
Stochastic min-max optimization has gained interest in the machine learning community with the advancements in GANs and adversarial training.
Synaptic Weight Distributions Depend on the Geometry of Plasticity
Overall, our work shows that the current paradigm in theoretical work on synaptic plasticity that assumes Euclidean synaptic geometry may be misguided and that it should be possible to experimentally determine the true geometry of synaptic plasticity in the brain.
Raising the Bar for Certified Adversarial Robustness with Diffusion Models
In this work, we demonstrate that a similar approach can substantially improve deterministic certified defenses.
Sarah Frank-Wolfe: Methods for Constrained Optimization with Best Rates and Practical Features
Moreover, our second approach does not require either large batches or full deterministic gradients, which is a typical weakness of many techniques for finite-sum problems.
Performative Prediction with Neural Networks
In this work, we instead assume that the data distribution is Lipschitz continuous with respect to the model's predictions, a more natural assumption for performative systems.
Feature Likelihood Divergence: Evaluating the Generalization of Generative Models Using Samples
The past few years have seen impressive progress in the development of deep generative models capable of producing high-dimensional, complex, and photo-realistic data.
High-Probability Bounds for Stochastic Optimization and Variational Inequalities: the Case of Unbounded Variance
During recent years the interest of optimization and machine learning communities in high-probability convergence of stochastic optimization methods has been growing.
When is Momentum Extragradient Optimal? A Polynomial-Based Analysis
The extragradient method has gained popularity due to its robust convergence properties for differentiable games.
Nesterov Meets Optimism: Rate-Optimal Separable Minimax Optimization
AG-OG is the first single-call algorithm with optimal convergence rates in both deterministic and stochastic settings for bilinearly coupled minimax optimization problems.
Dissecting adaptive methods in GANs
By considering an update rule with the magnitude of the Adam update and the normalized direction of SGD, we empirically show that the adaptive magnitude of Adam is key for GAN training.
The Curse of Unrolling: Rate of Differentiating Through Optimization
Computing the Jacobian of the solution of an optimization problem is a central problem in machine learning, with applications in hyperparameter optimization, meta-learning, optimization as a layer, and dataset distillation, to name a few.
Proceedings of the ICML 2022 Expressive Vocalizations Workshop and Competition: Recognizing, Generating, and Personalizing Vocal Bursts
The first, ExVo-MultiTask, requires participants to train a multi-task model to recognize expressed emotions and demographic traits from vocal bursts.
Generating Diverse Vocal Bursts with StyleGAN2 and MEL-Spectrograms
We describe our approach for the generative emotional vocal burst task (ExVo Generate) of the ICML Expressive Vocalizations Competition.
On the Limitations of Elo: Real-World Games, are Transitive, not Additive
In this study, we investigate the challenge of identifying the strength of the transitive component in games.
Only Tails Matter: Average-Case Universality and Robustness in the Convex Regime
The recently developed average-case analysis of optimization methods allows a more fine-grained and representative convergence analysis than usual worst-case results.
Optimal Extragradient-Based Bilinearly-Coupled Saddle-Point Optimization
We consider the smooth convex-concave bilinearly-coupled saddle-point problem, $\min_{\mathbf{x}}\max_{\mathbf{y}}~F(\mathbf{x}) + H(\mathbf{x},\mathbf{y}) - G(\mathbf{y})$, where one has access to stochastic first-order oracles for $F$, $G$ as well as the bilinear coupling function $H$.
A General Framework For Proving The Equivariant Strong Lottery Ticket Hypothesis
In this paper, we generalize the SLTH to functions that preserve the action of the group $G$ -- i. e. $G$-equivariant network -- and prove, with high probability, that one can approximate any $G$-equivariant network of fixed width and depth by pruning a randomly initialized overparametrized $G$-equivariant network to a $G$-equivariant subnetwork.
Clipped Stochastic Methods for Variational Inequalities with Heavy-Tailed Noise
In this work, we prove the first high-probability complexity results with logarithmic dependence on the confidence level for stochastic methods for solving monotone and structured non-monotone VIPs with non-sub-Gaussian (heavy-tailed) noise and unbounded domains.
Variance Reduction is an Antidote to Byzantines: Better Rates, Weaker Assumptions and Communication Compression as a Cherry on the Top
However, many fruitful directions, such as the usage of variance reduction for achieving robustness and communication compression for reducing communication costs, remain weakly explored in the field.
The ICML 2022 Expressive Vocalizations Workshop and Competition: Recognizing, Generating, and Personalizing Vocal Bursts
ExVo 2022, includes three competition tracks using a large-scale dataset of 59, 201 vocalizations from 1, 702 speakers.
Beyond L1: Faster and Better Sparse Models with skglm
We propose a new fast algorithm to estimate any sparse generalized linear model with convex or non-convex separable penalties.
Stochastic Extragradient: General Analysis and Improved Rates
The Stochastic Extragradient (SEG) method is one of the most popular algorithms for solving min-max optimization and variational inequalities problems (VIP) appearing in various machine learning tasks.
Generating Diverse Realistic Laughter for Interactive Art
We propose an interactive art project to make those rendered invisible by the COVID-19 crisis and its concomitant solitude reappear through the welcome melody of laughter, and connections created and explored through advanced laughter synthesis approaches.
Convergence Analysis and Implicit Regularization of Feedback Alignment for Deep Linear Networks
We theoretically analyze the Feedback Alignment (FA) algorithm, an efficient alternative to backpropagation for training neural networks.
Extragradient Method: $O(1/K)$ Last-Iterate Convergence for Monotone Variational Inequalities and Connections With Cocoercivity
In this paper, we resolve one of such questions and derive the first last-iterate $O(1/K)$ convergence rate for EG for monotone and Lipschitz VIP without any additional assumptions on the operator unlike the only known result of this type (Golowich et al., 2020) that relies on the Lipschitzness of the Jacobian of the operator.
Pick Your Battles: Interaction Graphs as Population-Level Objectives for Strategic Diversity
Strategic diversity is often essential in games: in multi-player games, for example, evaluating a player against a diverse set of strategies will yield a more accurate estimate of its performance.
Adam is no better than normalized SGD: Dissecting how adaptivity improves GAN performance
We empirically show that SGDA with the same vector norm as Adam reaches similar or even better performance than the latter.
A Distributional Robustness Perspective on Adversarial Training with the $\infty$-Wasserstein Distance
We show a formal connection between our formulation and optimal transport by relaxing AT into DRO problem with an $\infty$-Wasserstein constraint.
Generalized Natural Gradient Flows in Hidden Convex-Concave Games and GANs
In the case of Fisher information geometry, we provide a complete picture of the dynamics in an interesting special setting of team competition via invariant function analysis.
Stochastic Gradient Descent-Ascent and Consensus Optimization for Smooth Games: Convergence Analysis under Expected Co-coercivity
Two of the most prominent algorithms for solving unconstrained smooth games are the classical stochastic gradient descent-ascent (SGDA) and the recently introduced stochastic consensus optimization (SCO) [Mescheder et al., 2017].
On the Convergence of Stochastic Extragradient for Bilinear Games using Restarted Iteration Averaging
We study the stochastic bilinear minimax optimization problem, presenting an analysis of the same-sample Stochastic ExtraGradient (SEG) method with constant step size, and presenting variations of the method that yield favorable convergence.
A single gradient step finds adversarial examples on random two-layers neural networks
Daniely and Schacham recently showed that gradient descent finds adversarial examples on random undercomplete two-layers ReLU neural networks.
Online Adversarial Attacks
Adversarial attacks expose important vulnerabilities of deep learning models, yet little attention has been paid to settings where data arrives as a stream.
Adversarial Example Games
We introduce Adversarial Example Games (AEG), a framework that models the crafting of adversarial examples as a min-max game between a generator of attacks and a classifier.
Real World Games Look Like Spinning Tops
This paper investigates the geometrical properties of real world games (e. g. Tic-Tac-Toe, Go, StarCraft II).
A Limited-Capacity Minimax Theorem for Non-Convex Games or: How I Learned to Stop Worrying about Mixed-Nash and Love Neural Nets
Adversarial training, a special case of multi-objective optimization, is an increasingly prevalent machine learning technique: some of its most notable applications include GAN-based generative modeling and self-play techniques in reinforcement learning which have been applied to complex games such as Go or Poker.
Accelerating Smooth Games by Manipulating Spectral Shapes
Using this perspective, we propose an optimal algorithm for bilinear games.
Finite Regret and Cycles with Fixed Step-Size via Alternating Gradient Descent-Ascent
Gradient descent is arguably one of the most popular online optimization methods with a wide array of applications.
Computer Science and Game Theory Dynamical Systems Optimization and Control
Linear Lower Bounds and Conditioning of Differentiable Games
In this work, we approach the question of fundamental iteration complexity by providing lower bounds to complement the linear (i. e. geometric) upper bounds observed in the literature on a wide class of problems.
A Tight and Unified Analysis of Gradient-Based Methods for a Whole Spectrum of Games
We provide new analyses of the EG's local and global convergence properties and use is to get a tighter global convergence rate for OG and CO. Our analysis covers the whole range of settings between bilinear and strongly monotone games.
A Closer Look at the Optimization Landscapes of Generative Adversarial Networks
Generative adversarial networks have been very successful in generative modeling, however they remain relatively challenging to train compared to standard deep neural networks.
Non-normal Recurrent Neural Network (nnRNN): learning long time dependencies while improving expressivity with transient dynamics
A recent strategy to circumvent the exploding and vanishing gradient problem in RNNs, and to allow the stable propagation of signals over long time scales, is to constrain recurrent connectivity matrices to be orthogonal or unitary.
Painless Stochastic Gradient: Interpolation, Line-Search, and Convergence Rates
To improve the proposed methods' practical performance, we give heuristics to use larger step-sizes and acceleration.
Implicit Regularization of Discrete Gradient Dynamics in Linear Neural Networks
When optimizing over-parameterized models, such as deep neural networks, a large set of parameters can achieve zero training error.
Reducing Noise in GAN Training with Variance Reduced Extragradient
We study the effect of the stochastic gradient noise on the training of generative adversarial networks (GANs) and show that it can prevent the convergence of standard game optimization methods, while the batch version converges.
Negative Momentum for Improved Game Dynamics
Games generalize the single-objective optimization paradigm by introducing different objective functions for different players.
Frank-Wolfe Splitting via Augmented Lagrangian Method
In this work, we develop and analyze the Frank-Wolfe Augmented Lagrangian (FW-AL) algorithm, a method for minimizing a smooth function over convex compact sets related by a "linear consistency" constraint that only requires access to a linear minimization oracle over the individual constraints.
Adaptive Three Operator Splitting
We propose and analyze an adaptive step-size variant of the Davis-Yin three operator splitting.
A Variational Inequality Perspective on Generative Adversarial Networks
Generative adversarial networks (GANs) form a generative modeling approach known for producing appealing samples, but they are notably difficult to train.
Parametric Adversarial Divergences are Good Losses for Generative Modeling
Parametric adversarial divergences, which are a generalization of the losses used to train generative adversarial networks (GANs), have often been described as being approximations of their nonparametric counterparts, such as the Jensen-Shannon divergence, which can be derived under the so-called optimal discriminator assumption.
Frank-Wolfe Algorithms for Saddle Point Problems
We extend the Frank-Wolfe (FW) optimization algorithm to solve constrained smooth convex-concave saddle point (SP) problems.
