4 articles · sorted by date
If you use double/debiased machine learning to estimate an effect, you also need to know how uncertain that estimate is. The bootstrap—the familiar trick of resampling data to see how much answers move around—has been widely used for that job, but until now it lacked a general proof for these estimators. This paper closes that gap. The authors show that bootstrap inference is valid for a broad class of double/debiased machine learning estimators under exchangeably weighted resampling schemes, with Efron’s bootstrap included as a special case. The key point is striking: the bootstrap works under exactly the same conditions needed for double machine learning itself to be valid. In the paper’s words, the bootstrap law converges conditionally weakly to the sampling law of the original estimator. That matters because double machine learning is designed for modern settings with high-dimensional or otherwise complex nuisance components, where classical assumptions are often too restrictive. With this result, the resampling methods already suggested and used in practice now have theoretical backing.
Overnight interest rates can spike on dates everyone already knows will matter, like central bank meetings. This paper shows how to build that behavior into a classic short-rate model without breaking its core structure. The authors extend the Cox-Ingersoll-Ross (CIR) process, a standard model for interest rates, by allowing jumps at predetermined dates called stochastic discontinuities. Each jump size depends on the rate just before the jump, so the model can move both up and down and can even create dependence between jumps. The paper proves that such a process exists under mild assumptions, and it identifies when the extended model still keeps the affine property of the original CIR process. It also gives examples that preserve both non-negativity and affinity, including one built by applying a deterministic c`adl`ag time-change to a standard CIR process. Finally, the authors characterize when this richer CIR model is infinitely divisible, adding another piece to the affine modelling toolkit for overnight rates and other settings with scheduled jumps.
If you want to know when a complex system fails, the first event is only part of the story. This paper tackles the harder question: when does the nth coordinate in a many-body stochastic process reach a boundary, called a killing barrier, where that coordinate disappears from the dynamics? The author derives recursive formulas for the survival function and the nth first passage time distribution in jump and diffusion processes, beginning with two coordinates and then extending the result to three or more. The paper says these formulas are quite general, but also difficult to implement. To show they still have value, it applies them to single file diffusion, a physical system where movement is tightly constrained, and to pricing an nth-to-default credit default swap, a financial contract tied to successive defaults. The main takeaway is a mathematical framework for timing the nth event in systems where one failure is not the whole story.
Imagine an origami structure that doesn’t unfold all at once, but wakes up one crease at a time like a row of falling dominoes. This paper shows how to program that kind of orderly motion using geometry alone, without relying on stored elastic energy. The authors build a design framework for kinematic transition fronts, linking them to heteroclinic orbits in discrete dynamical systems. Focusing on strips of developable, flat-foldable degree-4 origami vertices, they show that asymmetric coupling between neighboring creases creates nonlinear recurrence relations that can connect fully developed and fully flat-folded states. That connection produces sequential deployment along the strip. The paper also shows that the overall macroscopic shape can be chosen independently of how the motion propagates, using invariances in the recurrence relation. A thick-panel origami prototype illustrates the idea. The result is a general way to design domino-like deployment in origami, and a broader framework for kinematic transition fronts in geometrically constrained systems.
