The Approximation Rank of Softmax Attention
Sharp Geometric Laws and Robust Interaction Dimension
Studies the approximation complexity of softmax attention through support geometry and softmax-visible interaction dimension.
Studies in learning, decision-making, and quantitative methods.
6 results
Sharp Geometric Laws and Robust Interaction Dimension
Studies the approximation complexity of softmax attention through support geometry and softmax-visible interaction dimension.
A hierarchical long-horizon research workflow centred on durable state, explicit handoffs, independent verification, recovery, and bounded agent authority.
A bounded transformer-news overlay for Chinese macro-asset allocation with explicit portfolio controls and frozen evaluation.
Microprice, order-book imbalance, and toxicity-adjusted factor variants examined through parameter sweeps and long–short validation.
A multi-period retirement-allocation study combining wealth, annuity adequacy, mortality assumptions, and later health-state extensions.
Empirical fixed-income research using a rule-based disclosure-risk score, issue-spread regressions, and conditional portfolio sorts.
No matching results. Try another keyword or clear the filters.