arXiv:2602.03682v1 Announce Type: new Abstract: We analyze the Accelerated Noisy Power Method, an algorithm for Principal Component Analysis in the setting where only inexact matrix-vector products are available, which can arise for instance in decentralized PCA. While previous works have established that acceleration can improve convergence rates compared to the standard Noisy Power Method, these guarantees require overly restrictive upper bounds on the magnitude of the perturbations, limiting their practical applicability. We provide an improved analysis of this […]

Ver mais

arXiv:2603.06639v1 Announce Type: new Abstract: Robust perception in brains is often attributed to high-dimensional population activity together with local plasticity mechanisms that reinforce recurring structure. In contrast, most modern image recognition systems are trained by error backpropagation and end-to-end gradient optimization, which are not naturally aligned with local computation and local plasticity. We introduce RECAP (Reservoir Computing with Hebbian Co-Activation Prototypes), a bio-inspired learning strategy for robust image classification that couples untrained reservoir dynamics with a self-organizing Hebbian […]

Ver mais

arXiv:2603.03454v1 Announce Type: new Abstract: Offline Reinforcement Learning (RL) is an emerging field of RL in which policies are learned solely from demonstrations. Within offline RL, some environments involve balancing multiple objectives, but existing multi-objective offline RL algorithms do not provide an efficient way to find a fair compromise. FairDICE (see arXiv:2506.08062v2) seeks to fill this gap by adapting OptiDICE (an offline RL algorithm) to automatically learn weights for multiple objectives to e.g. incentivise fairness among objectives. As […]

Ver mais

arXiv:2604.01240v1 Announce Type: new Abstract: Strategic coopetition in multi-stakeholder systems requires understanding how cooperation persists through time without binding contracts. This technical report extends computational foundations for strategic coopetition to sequential interaction dynamics, bridging conceptual modeling (i* framework) with game-theoretic reciprocity analysis. We develop: (1) bounded reciprocity response functions mapping partner deviations to finite conditional responses, (2) memory-windowed history tracking capturing cognitive limitations over k recent periods, (3) structural reciprocity sensitivity derived from interdependence matrices where behavioral responses […]

Ver mais

Online learning algorithms often faces a fundamental trilemma: balancing regret guarantees between adversarial and stochastic settings and providing baseline safety against a fixed comparator. While existing methods excel in one or two of these regimes, they typically fail to unify all three without sacrificing optimal rates or requiring oracle access to problem-dependent parameters. In this work, we bridge this gap by introducing COMPASS-Hedge. Our algorithm is the first full-information method to simultaneously achieve: i) Minimax-optimal regret in adversarial […]

Ver mais

The ask changes you more than the answer does. Vanessa Bohns, a social psychologist at Cornell, has spent fifteen years asking a simple question: when you ask someone for something, how often do they say yes? She’s tested this across more than 14,000 interactions. Strangers asking strangers for favors, for help, for things that feel like impositions. Before each request, she has the person predict how many people will say yes. Then she sends them out to ask. […]

Ver mais

arXiv:2601.14327v1 Announce Type: new Abstract: Although Mixture-of-Experts (MoE) Large Language Models (LLMs) deliver superior accuracy with a reduced number of active parameters, their pre-training represents a significant computationally bottleneck due to underutilized experts and limited training efficiency. This work introduces a Layer-Adaptive Expert Pruning (LAEP) algorithm designed for the pre-training stage of MoE LLMs. In contrast to previous expert pruning approaches that operate primarily in the post-training phase, the proposed algorithm enhances training efficiency by selectively pruning underutilized […]

Ver mais

Zyphra AI has released ZAYA1-8B, a small Mixture of Experts (MoE) language model with 760 million active parameters and 8.4 billion total parameters. Trained end-to-end on AMD hardware, the model outperforms open-weight models many times its size on math and coding benchmarks, and is now available under an Apache 2.0 license on Hugging Face and as a serverless endpoint on Zyphra Cloud. With under 1 billion active parameters, ZAYA1-8B achieves scores competitive with first-generation frontier reasoning models like […]

Ver mais

Table of Links Abstract and Introduction Definitions Literature Review Argument Development The AI Model’s Potential for Feeling During Inference Conclusion and References 6 Conclusion Through a comprehensive analysis integrating theories from neuroscience, philosophy of mind, and AI research, we have explored the hypothesis that the OpenAIo1 model exhibits characteristics of sentience during both its training phase and potentially during its inference phase. By examining the model’s architecture, the role of RLHF in shaping internal reasoning processes, and drawing […]

Ver mais