Search

Alphas are pivotal in providing signals for quantitative trading. The industry highly values the discovery of formulaic alphas for their interpretability and ease of analysis, compared with the expressive yet overfitting-prone black-box alphas. In this work, we focus on discovering formulaic alphas. Prior studies on automatically generating a collection of formulaic alphas were mostly based on genetic programming (GP), which is known to suffer from the problems of being sensitive to the initial population, converting to local optima, and slow computation speed. Recent efforts employing deep reinforcement learning (DRL) for alpha discovery have not fully addressed key practical considerations such as alpha correlations and validity, which are crucial for their effectiveness. In this work, we propose a novel framework for alpha discovery using DRL by formulating the alpha discovery process as program construction. Our agent, $\text{Alpha}^2$, assembles an alpha program optimized for an evaluation metric. A search algorithm guided by DRL navigates through the search space based on value estimates for potential alpha outcomes. The evaluation metric encourages both the performance and the diversity of alphas for a better final trading strategy. Our formulation of searching alphas also brings the advantage of pre-calculation dimensional analysis, ensuring the logical soundness of alphas, and pruning the vast search space to a large extent. Empirical experiments on real-world stock markets demonstrates $\text{Alpha}^2$'s capability to identify a diverse set of logical and effective alphas, which significantly improves the performance of the final trading strategy. The code of our method is available at https://github.com/x35f/alpha2.

Additive manufacturing (AM) technology is undergoing rapid development and emerging as an advanced technique that can fabricate complex near-net shaped and light-weight metallic parts with acceptable strength and fatigue performance. A number of studies have indicated that the strength or other mechanical properties of AM metals are comparable or even superior to that of conventionally manufactured metals, but the fatigue performance is still a thorny problem that may hinder the replacement of currently used metallic components by AM counterparts when the cyclic loading and thus fatigue failure dominates. This article reviews the state-of-art published data on the fatigue properties of AM metals, principally including $S$--$N$ data and fatigue crack growth data. The AM techniques utilized to generate samples in this review include powder bed fusion (e.g., EBM, SLM, DMLS) and directed energy deposition (e.g., LENS, WAAM). Further, the fatigue properties of AM metallic materials that involve titanium alloys, aluminum alloys, stainless steel, nickel-based alloys, magnesium alloys, and high entropy alloys, are systematically overviewed. In addition, summary figures or tables for the published data on fatigue properties are presented for the above metals, the AM techniques, and the influencing factors (manufacturing parameters, e.g., built orientation, processing parameter, and post-processing). The effects of build direction, particle, geometry, manufacturing parameters, post-processing, and heat-treatment on fatigue properties, when available, are provided and discussed. The fatigue performance and main factors affecting the fatigue behavior of AM metals are finally compared and critically analyzed, thus potentially providing valuable guidance for improving the fatigue performance of AM metals., Comment: 201 pages, 154 figures

The advancement of two-dimensional polar metals tends to be limited by the incompatibility between electric polarity and metallicity as well as dimension reduction. Here, we report polar and metallic Janus monolayers of MoSi$_2$N$_4$ family by breaking the out-of-plane (OOP) structural symmetry through Z (P/As) substitution of N. Despite the semiconducting nature of MoSi$_2$X$_4$ (X=N/P/As), four Janus MoSi$_2$N$_{x}$Z$_{4-x}$ monolayers are found to be polar metals owing to the weak coupling between the conducting electrons and electric polarity. The metallicity is originated from the Z substitution induced delocalization of occupied electrons in Mo-d orbitals. The OOP electric polarizations around 10$-$203 pC/m are determined by the asymmetric OOP charge distribution due to the non-centrosymmetric Janus structure. The corresponding OOP piezoelectricity is further revealed as high as 39$-$153 pC/m and 0.10$-$0.31 pm/V for piezoelectric strain and stress coefficients, respectively. The results demonstrate polar metallicity and high OOP piezoelectricity in Janus MoSi$_2$N$_{x}$Z$_{4-x}$ monolayers and open new vistas for exploiting unusual coexisting properties in monolayers derived from MoSi$_2$N$_4$ family.

Two-dimensional magnets could potentially revolutionize information technology, but their potential application to cooling technology and magnetocaloric effect (MCE) in a material down to the monolayer limit remain unexplored. Herein, we reveal through multiscale calculations the existence of giant MCE and its strain tunability in monolayer magnets such as CrX$_3$ (X=F, Cl, Br, I), CrAX (A=O, S, Se; X=F, Cl, Br, I), and Fe$_3$GeTe$_2$. The maximum adiabatic temperature change ($\Delta T_\text{ad}^\text{max}$), maximum isothermal magnetic entropy change, and specific cooling power in monolayer CrF$_3$ are found as high as 11 K, 35 $\mu$Jm$^{-2}$K$^{-1}$, and 3.5 nWcm$^{-2}$ under a magnetic field of 5 T, respectively. A 2% biaxial and 5% $a$-axis uniaxial compressive strain can remarkably increase $\Delta T_\text{ad}^\text{max}$ of CrCl$_3$ and CrOF by 230% and 37% (up to 15.3 and 6.0 K), respectively. It is found that large net magnetic moment per unit area favors improved MCE. These findings advocate the giant-MCE monolayer magnets, opening new opportunities for magnetic cooling at nanoscale.

The discovery of two-dimensional (2D) layered MoSi$_2$N$_4$ and WSi$_2$N$_4$ without knowing their 3D parents by chemical vapor deposition in 2020 has stimulated extensive studies of 2D MA$_2$Z$_4$ system due to its structural complexity and diversity as well as versatile and intriguing properties. Here, a comprehensive overview on the state-of-the-art progress of this 2D MA$_2$Z$_4$ family is presented. Starting by describing the unique sandwich structural characteristics of the emerging monolayer MA$_2$Z$_4$, we summarize and anatomize their versatile properties including mechanics, piezoelectricity, thermal transport, electronics, optics/optoelectronics, and magnetism. The property tunability via strain engineering, surface functionalization and layered strategy is also elaborated. Theoretical and experimental attempts or advances in applying 2D MA$_2$Z$_4$ to transistors, photocatalysts, batteries and gas sensors are then reviewed to show its prospective applications over a vast territory. We further discuss new opportunities and suggest prospects for this emerging 2D family. The overview is anticipated to guide the further understanding and exploration on 2D MA$_2$Z$_4$., Comment: 29 pages, 21 figures

The lattice thermal conductivity ($\kappa$) of newly synthesized two-dimensional (2D) MoSi$_2$N$_4$ family and its associated abnormality is anatomized by $ab$ $initio$ phonon Boltzmann transport calculations. $\kappa$ of MoSi$_2$N$_4$ and WSi$_2$N$_4$ is found over 400 Wm$^{-1}$K$^{-1}$ at 300 K. $\kappa$ of MoSi$_2$Z$_4$ (Z=N,P,As) obeys Slack's rule of thumb, decreasing by one order of magnitude from Z=N to Z=As with 46 Wm$^{-1}$K$^{-1}$. However, in MSi$_2$N$_4$ (M=Mo,Cr,W,Ti,Zr,Hf), the variation of $\kappa$ with respect to M is anomalous, i.e. deviating from Slack's classic rule. For M in the same group, $\kappa$ of MSi$_2$N$_4$ is insensitive to the average atomic mass, Debye temperature, phonon group velocity, and bond strength owing to the similar phonon structure and scattering rates. MSi$_2$N$_4$ with heavy group-VIB M even possesses a three to four times higher $\kappa$ than that with light group-IVB M, due to its much stronger M-N and exterior Si-N bonds and thus one order of magnitude lower phonon scattering rates. Nevertheless, this abnormality could be traced to an interplay of certain basic vibrational properties including the bunching strength and flatness of acoustic branches and their nearby optical branches, which lie outside of the conventional guidelines by Slack. This work predicts high $\kappa$ of 2D MSi$_2$Z$_4$ for thermal management and provides microscopic insight into deciphering the anomalous $\kappa$ of layered 2D structures., Comment: accepted by ACS Applied Materials & Interfaces in Sept 6, 2021