Searcharxiv⌕ Search

arXiv subjects

Shoichiro Tanaka

Publications and source records attributed to Shoichiro Tanaka.

4 recordsLinked to original sources

Shortcut Learning in Feature-Based Algorithm Selection

Landscape features give learning models information about the objective function for algorithm selection, algorithm configuration, and performance prediction. Should these features capture more information? Not always, because a model may rely on information that the algorithms ignore. This phenomenon is called shortcut learning, and in-distribution accuracy can hide it. We propose the Rubber Ruler Test. It transforms the objective values of test instances with random strictly increasing transformations, reruns the algorithms, and measures prediction performance. Comparison-based algorithms such as CMA-ES perform identically after the transformation, so for them any drop reveals shortcut learning. On 10-dimensional BBOB, a model for two comparison-based algorithms learned shortcuts even from normalized objective values. The R^2 of a model using all ELA features dropped from 0.85 to 0.23, below 0.45 with invariant features only. Rank-based features reduced the drop when algorithms search using ranks. Data augmentation with transformed training instances improved prediction on transformed instances for every portfolio we studied, but lowered R^2 on original instances by up to 0.31. These results suggest that models should rely only on information that the algorithms use. We recommend reporting the Rubber Ruler Test alongside in-distribution accuracy and using it to choose feature extraction and data augmentation.

cs.NE↗

Impacts of Single-objective Landscapes on Multi-objective Optimization

This work revealed a relationship between a multi-objective optimization problem and single-objective optimization problems that exist in the multi-objective problem. This work focused on combinatorial problems and investigated the relations between the local optima networks of the single-objective problems and the Pareto optima network of the multi-objective problem. Each of their networks has a graph structure. We divided the entire network into subgraphs. Each subgraph was called a component and characterized by overlapping relations between the single-objective local optima networks and the multi-objective Pareto optima network. Results on multi-objective landscape problems showed that most Pareto optimal solutions were reachable from the single-objective local optimal solutions. This tendency was emphasized by increasing the number of objectives and the objective correlation. The number of co-variables impacted the number of cross-link relations between the single-objective local optima networks and the multi-objective Pareto optima network. The results suggested that searching for single-objective problems is a clue to multi-objective optimization.

cs.NE↗

Novelty-Based Generation of Continuous Landscapes with Diverse Local Optima Networks

Local Optima Networks (LONs) represent the global structure of search spaces as graphs, but their construction requires iterative execution of a search algorithm to find local optima and approximate transitions between Basins of Attraction (BoAs). In continuous optimization, this high computational cost prevents systematic investigation of the relationship between LON features and evolutionary algorithm performance. To address this issue, we propose an alternative definition of BoAs for Max-Set of Gaussians (MSG) landscapes with explicitly tunable multimodality. This bypasses search-based BoA identification, enabling low-cost LON construction. Moreover, we leverage Novelty Search (NS) to explore the parameter space of the MSG landscape generator, producing instances with diverse graph topologies. Our experiments show that the proposed BoAs closely align with gradient-based BoAs, and that NS successfully generates instances with varied search difficulty and connectivity patterns among optima. Finally, over the instances generated by NS, we predict the success rate of two well-established evolutionary algorithms from LON features. While our LON construction is specific to MSG landscapes, the proposed framework provides a dataset that serves as a foundation for landscape-aware optimization.

cs.NE↗

Detectability of CMB Weak Lensing and HI Cross Correlation and constraints on cosmological parameters

Neutral hydrogen (H$_{\rm I}$) intensity mapping is capable of measuring redshift evolution of H$_{\rm I}$ density parameter $Ω_{\rm H_{\rm I}}$, which is an important parameter to understand structure formation in the post-reionization epoch. Future H$_{\rm I}$ observation with Square Kilometre Array (SKA) can significantly improve constraints on the parameter. However, the observation of H$_{\rm I}$ suffers from the contamination from extremely bright foreground emissions, and it is necessary to consider a signal validation method complementary to the measurement of H$_{\rm I}$ auto power spectrum. In this work, we propose to take a cross correlation between a 21cm-line intensity map and a convergence map reconstructed from observation of the cosmic microwave background by Planck and estimate expected ideal constraints on cosmological parametersby ignoring the foreground contamination. We find that the SKA1-mid operated in single-dish mode has a sufficient capability to detect the cross correlation on the large scales. Further, by Fisher analysis assuming a constant linear bias of H$_{\rm I}$, $b$, and SKA1-mid observation of 1,000 hours for each of Band 1 and 2, we show that $Ω_{\rm H_{\rm I}} b$ can be constrained with a precision of $6-13\%$ at a wide range of redshifts of $0.0<z<2.0$, if we fix other cosmological parameters (density parameter of cold dark matter, $Ω_{\rm c} h^{2}$, spectral index of primordial fluctuations, $n_s$, and Hubble constant, $H_0$) using values from the Planck observations. On the other hand, small-scale measurements with interferometer mode of SKA1-mid will not have a significant impact on constraining the parameters with 1,000 hours of observation time for each of Band 1 and 2, due to the limited resolution of the CMB lensing of Planck.

astro-ph.CO↗