Among existing Neural Architecture Search methods, DARTS is known for its efficiency and simplicity. This approach applies continuous relaxation of network representation to construct a weight-sharing supernet and enables the identification of excellent subnets in just a few GPU days. However, performance collapse in DARTS results in deteriorating architectures filled with parameter-free operations and remains a great challenge to the robustness. To resolve this problem, we reveal that the fundamental reason is the biased estimation of the candidate importance in the search space through theoretical and experimental analysis, and more precisely select operations via information-based measurements. Furthermore, we demonstrate that the excessive concern over the supernet and inefficient utilization of data in bi-level optimization also account for suboptimal results. We adopt a more realistic objective focusing on the performance of subnets and simplify it with the help of the information-based measurements. Finally, we explain theoretically why progressively shrinking the width of the supernet is necessary and reduce the approximation error of optimal weights in DARTS. Our proposed method, named IS-DARTS, comprehensively improves DARTS and resolves the aforementioned problems. Extensive experiments on NAS-Bench-201 and DARTS-based search space demonstrate the effectiveness of IS-DARTS.

The new centre shall undertake leading-edge research in data science and Artificial Intelligence that will support businesses, governance, and policymaking, the top B-School said. "It aims to forge…collaborative relationships between scholars and practitioners in data-intensive organisations, besides undertaking case-based research to understand the current industry practice and develop case studies for classroom teaching," the business school said. Announcing the launch of the centre, Errol D'Souza, director, IIM A, said, "Data Science and Artificial Intelligence are increasingly impacting businesses across the world. AI has become an inevitable part of our lives. To harness the power of these advanced technologies for augmenting businesses, the need of the hour is to bring together different stakeholders onto the same platform, conduct intensive research to identify challenges, determine potential and provide impactful insights".