Zobrazeno 1 - 10
of 19 679
pro vyhledávání: '"A. Daskalakis"'
Learning algorithms are often used to make decisions in sequential decision-making environments. In multi-agent settings, the decisions of each agent can affect the utilities/losses of the other agents. Therefore, if an agent is good at anticipating
Externí odkaz:
http://arxiv.org/abs/2407.04889
Autor:
Dagan, Yuval, Daskalakis, Constantinos, Fishelson, Maxwell, Golowich, Noah, Kleinberg, Robert, Okoroafor, Princewill
A set of probabilistic forecasts is calibrated if each prediction of the forecaster closely approximates the empirical distribution of outcomes on the subset of timesteps where that prediction was made. We study the fundamental problem of online cali
Externí odkaz:
http://arxiv.org/abs/2406.13668
Autor:
Daskalakis, Constantinos, Farina, Gabriele, Golowich, Noah, Sandholm, Tuomas, Zhang, Brian Hu
Recent simultaneous works by Peng and Rubinstein [2024] and Dagan et al. [2024] have demonstrated the existence of a no-swap-regret learning algorithm that can reach $\epsilon$ average swap regret against an adversary in any extensive-form game withi
Externí odkaz:
http://arxiv.org/abs/2406.13116
The empirical risk minimization (ERM) principle has been highly impactful in machine learning, leading both to near-optimal theoretical guarantees for ERM-based learning algorithms as well as driving many of the recent empirical successes in deep lea
Externí odkaz:
http://arxiv.org/abs/2406.11667
We study computational and statistical aspects of learning Latent Markov Decision Processes (LMDPs). In this model, the learner interacts with an MDP drawn at the beginning of each epoch from an unknown mixture of MDPs. To sidestep known impossibilit
Externí odkaz:
http://arxiv.org/abs/2406.07920
Organic light-emitting diodes (OLEDs) have redefined lighting with their environment-friendliness and flexibility. However, only 25 % of the electronic states of fluorescent molecules can emit light upon electrical excitation, limiting the overall ef
Externí odkaz:
http://arxiv.org/abs/2404.04257
Ambient diffusion is a recently proposed framework for training diffusion models using corrupted data. Both Ambient Diffusion and alternative SURE-based approaches for learning diffusion models from corrupted data resort to approximations which deter
Externí odkaz:
http://arxiv.org/abs/2404.10177
While Online Gradient Descent and other no-regret learning procedures are known to efficiently converge to a coarse correlated equilibrium in games where each agent's utility is concave in their own strategy, this is not the case when utilities are n
Externí odkaz:
http://arxiv.org/abs/2403.08171
We provide a novel reduction from swap-regret minimization to external-regret minimization, which improves upon the classical reductions of Blum-Mansour [BM07] and Stolz-Lugosi [SL05] in that it does not require finiteness of the space of actions. We
Externí odkaz:
http://arxiv.org/abs/2310.19786
Autor:
Leppälä, Timo, Abdelmagid, Ahmed Gaber, Qureshi, Hassan A., Daskalakis, Konstantinos S., Luoma, Kimmo
Hybridisation of the cavity modes and the excitons to polariton states together with the coupling to the vibrational modes determine the linear optical properties of organic semiconductors in microcavities. In this article we compute the refractive i
Externí odkaz:
http://arxiv.org/abs/2310.19162