5 citations · 21 across the 23 of their papers we have counts for
27 papers
CAT-Flow: Curvature-Adaptive sTeps for Flow Matching
Qinchan Li, Pedro Cisneros-Velarde, Keru Fu +3
Flow Matching has emerged as a leading framework for generative modeling, powering state-of-the-art systems such as FLUX and Stable Diffusion 3.5. However, the iterative nature of…
Policy Compliance of User Requests in Natural Language for AI Systems
Pedro Cisneros-Velarde
Consider an organization whose users send requests in natural language to an AI system that fulfills them by carrying out specific tasks. In this paper, we consider the problem of…
Can One-sided Arguments Lead to Response Change in Large Language Models?
Pedro Cisneros-Velarde
Polemic questions need more than one viewpoint to express a balanced answer. Large Language Models (LLMs) can provide a balanced answer, but also take a single aligned viewpoint or…
GTAlign: Game-Theoretic Alignment of LLM Assistants for Social Welfare
Siqi Zhu, David Zhang, Pedro Cisneros-Velarde +1
Large Language Models (LLMs) have achieved remarkable progress in reasoning, yet sometimes produce responses that are suboptimal for users in tasks such as writing, information see…
Bypassing Safety Guardrails in LLMs Using Humor
Pedro Cisneros-Velarde
In this paper, we show it is possible to bypass the safety guardrails of large language models (LLMs) through a humorous prompt including the unsafe request. In particular, our met…
Optimization for Neural Operators can Benefit from Width
Pedro Cisneros-Velarde, Bhavesh Shrimali, Arindam Banerjee
Neural Operators that directly learn mappings between function spaces, such as Deep Operator Networks (DONs) and Fourier Neural Operators (FNOs), have received considerable attenti…
Large Language Models can Achieve Social Balance
Pedro Cisneros-Velarde
Large Language Models (LLMs) can be deployed in situations where they process positive/negative interactions with other agents. We study how this is done under the sociological fra…
Optimization and Generalization Guarantees for Weight Normalization
Pedro Cisneros-Velarde, Zhijie Chen, Sanmi Koyejo +1
Weight normalization (WeightNorm) is widely used in practice for the training of deep neural networks and modern deep learning libraries have built-in implementations of it. In thi…
On the Principles behind Opinion Dynamics in Multi-Agent Systems of Large Language Models
Pedro Cisneros-Velarde
We study the evolution of opinions inside a population of interacting large language models (LLMs). Every LLM needs to decide how much funding to allocate to an item with three ini…
Finite-sample Guarantees for Nash Q-learning with Linear Function Approximation
Pedro Cisneros-Velarde, Sanmi Koyejo
Nash Q-learning may be considered one of the first and most known algorithms in multi-agent reinforcement learning (MARL) for learning policies that constitute a Nash equilibrium o…
Restricted Strong Convexity of Deep Learning Models with Smooth Activations
Arindam Banerjee, Pedro Cisneros-Velarde, Libin Zhu +1
We consider the problem of optimization of deep learning models with smooth activation functions. While there exist influential results on the problem from the ``near initializatio…
Discrete State-Action Abstraction via the Successor Representation
Amnon Attali, Pedro Cisneros-Velarde, Marco Morales +1
While the difficulty of reinforcement learning problems is typically related to the complexity of their state spaces, Abstraction proposes that solutions often lie in simpler under…
One Policy is Enough: Parallel Exploration with a Single Policy is Near-Optimal for Reward-Free Reinforcement Learning
Pedro Cisneros-Velarde, Boxiang Lyu, Sanmi Koyejo +1
Although parallelism has been extensively used in reinforcement learning (RL), the quantitative effects of parallel exploration are not well understood theoretically. We study the…
Family-wise error rate control in Gaussian graphical model selection via Distributionally Robust Optimization
Chau Tran, Pedro Cisneros-Velarde, Sang-Yun Oh +1
Recently, a special case of precision matrix estimation based on a distributionally robust optimization (DRO) framework has been shown to be equivalent to the graphical lasso. From…
From Contraction Theory to Fixed Point Algorithms on Riemannian and Non-Euclidean Spaces
Francesco Bullo, Pedro Cisneros-Velarde, Alexander Davydov +1
The design of fixed point algorithms is at the heart of monotone operator theory, convex analysis, and of many modern optimization problems arising in machine learning and control.…
A Contraction Theory Approach to Optimization Algorithms from Acceleration Flows
Pedro Cisneros-Velarde, Francesco Bullo
Much recent interest has focused on the design of optimization algorithms from the discretization of an associated optimization flow, i.e., a system of differential equations (ODEs…
Distributed Wasserstein Barycenters via Displacement Interpolation
Pedro Cisneros-Velarde, Francesco Bullo
Consider a multi-agent system whereby each agent has an initial probability measure. In this paper, we propose a distributed algorithm based upon stochastic, asynchronous and pairw…
Contraction Theory for Dynamical Systems on Hilbert Spaces
Pedro Cisneros-Velarde, Saber Jafarpour, Francesco Bullo
Contraction theory for dynamical systems on Euclidean spaces is well-established. For contractive (resp. semi-contractive) systems, the distance (resp. semi-distance) between any t…
Multi-group SIS Epidemics with Simplicial and Higher-Order Interactions
Pedro Cisneros-Velarde, Francesco Bullo
This paper analyzes a Susceptible-Infected-Susceptible (SIS) model of epidemic propagation over hypergraphs and, motivated by an important special case, we refer to the model as to…
Weak and Semi-Contraction for Network Systems and Diffusively-Coupled Oscillators
Saber Jafarpour, Pedro Cisneros-Velarde, Francesco Bullo
We develop two generalizations of contraction theory, namely, semi-contraction and weak-contraction theory. First, using the notion of semi-norm, we propose a geometric framework f…
Distributed and time-varying primal-dual dynamics via contraction analysis
Pedro Cisneros-Velarde, Saber Jafarpour, Francesco Bullo
In this note, we provide an overarching analysis of primal-dual dynamics associated to linear equality-constrained optimization problems using contraction analysis. For the well-kn…
A Network Formation Game for the Emergence of Hierarchies
Pedro Cisneros-Velarde, Francesco Bullo
We propose a novel network formation game that explains the emergence of various hierarchical structures in groups where self-interested or utility-maximizing individuals decide to…
Structural Balance via Gradient Flows over Signed Graphs
Pedro Cisneros-Velarde, Noah E. Friedkin, Anton V. Proskurnikov +1
Structural balance is a classic property of signed graphs satisfying Heider's seminal axioms. Mathematical sociologists have studied balance theory since its inception in the 1040s…
Distributionally Robust Formulation and Model Selection for the Graphical Lasso
Pedro Cisneros-Velarde, Sang-Yun Oh, Alexander Petersen
Building on a recent framework for distributionally robust optimization, we consider estimation of the inverse covariance matrix for multivariate data. We provide a novel notion of…