Zobrazeno 1 - 10
of 83 605
pro vyhledávání: '"A. Ioan"'
Autor:
Bot, Radu Ioan, Sonntag, Konstantin
In this paper we introduce, in a Hilbert space setting, a second order dynamical system with asymptotically vanishing damping and vanishing Tikhonov regularization that approaches a multiobjective optimization problem with convex and differentiable c
Externí odkaz:
http://arxiv.org/abs/2411.18422
Autor:
Ahmad, Ahmad, Kermanshah, Mehdi, Leahy, Kevin, Serlin, Zachary, Siu, Ho Chit, Mann, Makai, Vasile, Cristian-Ioan, Tron, Roberto, Belta, Calin
In this paper, we tackle the challenging problem of delayed rewards in reinforcement learning (RL). While Proximal Policy Optimization (PPO) has emerged as a leading Policy Gradient method, its performance can degrade under delayed rewards. We introd
Externí odkaz:
http://arxiv.org/abs/2411.17861
Autor:
Fomin, Fedor V., Fraigniaud, Pierre, Golovach, Petr A., Montealegre, Pedro, Rapaport, Ivan, Todinca, Ioan
We show that for every first-order logic (FO) formula $\varphi$, and every graph class $\mathcal{G}$ of bounded expansion, there exists a distributed (deterministic) algorithm that, for every $n$-node graph $G\in\mathcal{G}$ of diameter $D$, decides
Externí odkaz:
http://arxiv.org/abs/2411.14825
This paper introduces a novel model compression approach through dynamic layer-specific pruning in Large Language Models (LLMs), enhancing the traditional methodology established by SliceGPT. By transitioning from constant to dynamic slicing, our met
Externí odkaz:
http://arxiv.org/abs/2411.03513
Autor:
Gassmann, Loïc, Manolescu, Ioan
By the FKG inequality for FK-percolation, the probability of the alternating two-arm event is smaller than the product of the probabilities of having a primal arm and a dual arm, respectively. In this paper, we improve this inequality by a polynomial
Externí odkaz:
http://arxiv.org/abs/2410.23013
Spike Timing-Dependent Plasticity (STDP) is a promising substitute to backpropagation for local training of Spiking Neural Networks (SNNs) on neuromorphic hardware. STDP allows SNNs to address classification tasks by combining unsupervised STDP for f
Externí odkaz:
http://arxiv.org/abs/2410.17066
Autor:
Boţ, Radu Ioan, Chenchene, Enis
In this paper, we introduce a novel Extra-Gradient method with anchor term governed by general parameters. Our method is derived from an explicit discretization of a Tikhonov-regularized monotone flow in Hilbert space, which provides a theoretical fo
Externí odkaz:
http://arxiv.org/abs/2410.14369
Autor:
Paluch, Patrick, Spiecker, Martin, Gosling, Nicolas, Adam, Viktor, Kammhuber, Jakob, Vermeulen, Kiefer, Bouman, Daniël, Wernsdorfer, Wolfgang, Pop, Ioan M.
With the demand for scalable cryogenic microwave circuitry continuously rising, recently developed flexible microwave striplines offer the tantalyzing perspective of increasing the cabling density by an order of magnitude without thermally overloadin
Externí odkaz:
http://arxiv.org/abs/2410.01053
Autor:
Yang, Ze, Chen, George, Zhang, Haowei, Ta, Kevin, Bârsan, Ioan Andrei, Murphy, Daniel, Manivasagam, Sivabalan, Urtasun, Raquel
Self-driving vehicles (SDVs) require accurate calibration of LiDARs and cameras to fuse sensor data accurately for autonomy. Traditional calibration methods typically leverage fiducials captured in a controlled and structured scene and compute corres
Externí odkaz:
http://arxiv.org/abs/2409.18953
Autor:
Atanasova, Desislava G., Yang, Ian, Hönigl-Decrinis, Teresa, Gusenkova, Daria, Pop, Ioan M., Kirchmair, Gerhard
Quantum computation with bosonic modes presents a powerful paradigm for harnessing the principles of quantum mechanics to perform complex information processing tasks. In constructing a bosonic qubit with superconducting circuits, nonlinearity is typ
Externí odkaz:
http://arxiv.org/abs/2409.07612