Ammar Fayad | Searcharxiv

arXiv2026

Exact Law of Quantum Reversibility under Gaussian Pure Loss

Classical reverse diffusion is generated by changing the drift at fixed noise. We show that the quantum version of this principle obeys an exact law with a sharp phase boundary. For Gaussian pure-loss dynamics -- the canonical model of continuous-variable decoherence in optical attenuation channels, squeezed-light interferometric sensing, and superconducting bosonic architectures -- complete positivity, the requirement that the dynamics remain physical even for systems entangled with an ancilla, creates an exact phase boundary at which the minimum reverse cost vanishes, fixes the reverse-noise budget on both sides, and makes pure nonclassical targets dynamically singular. The minimum reverse cost vanishes exactly at a critical squeezing-to-thermal ratio and is strictly positive away from it, with a sharp asymmetry: below the boundary, standard reverse prescriptions such as the fixed-diffusion Bayes reverse remain feasible at mild cost; above it, these prescriptions become infeasible, the covariance-aligned generator remains CP-feasible and uniquely optimal, and the cost can be severe. The optimal reverse noise is locked to the state's own fluctuation geometry and simultaneously minimizes the geometric, metrological, and thermodynamic price of reversal. For multimode trajectories, the exact cost is additive in a canonical set of mode-resolved data, and a globally continuous protocol attains this optimum on every mixed-state interval. If a pure nonclassical endpoint is included, the same pointwise law holds for every $t>0$, but the optimum diverges as $2/t$: exact reversal of a pure quantum state is dynamically unattainable. These results establish an exact law of quantum reversibility in the canonical pure-loss setting and provide a sharp benchmark for broader theories of quantum reverse diffusion.

quant-ph↗

arXiv2026

Score Reversal Is Not Free for Quantum Diffusion Models

Classical reverse diffusion is generated by changing the drift at fixed noise. We show that the quantum version of this principle obeys an exact law with a sharp phase boundary. For Gaussian pure-loss dynamics, the canonical model of continuous-variable decoherence, we prove that the unrestricted instantaneous reverse optimum exhibits a noiseless-to-noisy transition: below a critical squeezing-to-thermal ratio, reversal can be noiseless; above it, complete positivity forces irreducible reverse noise whose minimum cost we determine in closed form. The optimal reverse diffusion is uniquely covariance-aligned and simultaneously minimizes the geometric, metrological, and thermodynamic price of reversal. For multimode trajectories, the exact cost is additive in a canonical set of mode-resolved data, and a globally continuous protocol attains this optimum on every mixed-state interval. If a pure nonclassical endpoint is included, the same pointwise law holds for every $t>0$, but the optimum diverges as $2/t$: exact Gaussian reversal of a pure quantum state is dynamically unattainable. These results establish the exact Gaussian benchmark against which any broader theory of quantum reverse diffusion must be measured.

quant-ph↗

arXiv2024

Unsupervised Learning Approach to Anomaly Detection in Gravitational Wave Data

Gravitational waves (GW), predicted by Einstein's General Theory of Relativity, provide a powerful probe of astrophysical phenomena and fundamental physics. In this work, we propose an unsupervised anomaly detection method using variational autoencoders (VAEs) to analyze GW time-series data. By training on noise-only data, the VAE accurately reconstructs noise inputs while failing to reconstruct anomalies, such as GW signals, which results in measurable spikes in the reconstruction error. The method was applied to data from the LIGO H1 and L1 detectors. Evaluation on testing datasets containing both noise and GW events demonstrated reliable detection, achieving an area under the ROC curve (AUC) of 0.89. This study introduces VAEs as a robust, unsupervised approach for identifying anomalies in GW data, which offers a scalable framework for detecting known and potentially new phenomena in physics.

gr-qc↗

arXiv2022

Hierarchical Strategies for Cooperative Multi-Agent Reinforcement Learning

Adequate strategizing of agents behaviors is essential to solving cooperative MARL problems. One intuitively beneficial yet uncommon method in this domain is predicting agents future behaviors and planning accordingly. Leveraging this point, we propose a two-level hierarchical architecture that combines a novel information-theoretic objective with a trajectory prediction model to learn a strategy. To this end, we introduce a latent policy that learns two types of latent strategies: individual $z_A$, and relational $z_R$ using a modified Graph Attention Network module to extract interaction features. We encourage each agent to behave according to the strategy by conditioning its local $Q$ functions on $z_A$, and we further equip agents with a shared $Q$ function that conditions on $z_R$. Additionally, we introduce two regularizers to allow predicted trajectories to be accurate and rewarding. Empirical results on Google Research Football (GRF) and StarCraft (SC) II micromanagement tasks show that our method establishes a new state of the art being, to the best of our knowledge, the first MARL algorithm to solve all super hard SC II scenarios as well as the GRF full game with a win rate higher than $95\%$, thus outperforming all existing methods. Videos and brief overview of the methods and results are available at: https://sites.google.com/view/hier-strats-marl/home.

cs.LG↗

arXiv2021

Influence-Based Reinforcement Learning for Intrinsically-Motivated Agents

Discovering successful coordinated behaviors is a central challenge in Multi-Agent Reinforcement Learning (MARL) since it requires exploring a joint action space that grows exponentially with the number of agents. In this paper, we propose a mechanism for achieving sufficient exploration and coordination in a team of agents. Specifically, agents are rewarded for contributing to a more diversified team behavior by employing proper intrinsic motivation functions. To learn meaningful coordination protocols, we structure agents' interactions by introducing a novel framework, where at each timestep, an agent simulates counterfactual rollouts of its policy and, through a sequence of computations, assesses the gap between other agents' current behaviors and their targets. Actions that minimize the gap are considered highly influential and are rewarded. We evaluate our approach on a set of challenging tasks with sparse rewards and partial observability that require learning complex cooperative strategies under a proper exploration scheme, such as the StarCraft Multi-Agent Challenge. Our methods show significantly improved performances over different baselines across all tasks.

cs.LG↗

arXiv2021

Behavior-Guided Actor-Critic: Improving Exploration via Learning Policy Behavior Representation for Deep Reinforcement Learning

In this work, we propose Behavior-Guided Actor-Critic (BAC), an off-policy actor-critic deep RL algorithm. BAC mathematically formulates the behavior of the policy through autoencoders by providing an accurate estimation of how frequently each state-action pair was visited while taking into consideration state dynamics that play a crucial role in determining the trajectories produced by the policy. The agent is encouraged to change its behavior consistently towards less-visited state-action pairs while attaining good performance by maximizing the expected discounted sum of rewards, resulting in an efficient exploration of the environment and good exploitation of all high reward regions. One prominent aspect of our approach is that it is applicable to both stochastic and deterministic actors in contrast to maximum entropy deep reinforcement learning algorithms. Results show considerably better performances of BAC when compared to several cutting-edge learning algorithms.

cs.LG↗