This document contains theorem proofs and algorithms for Avoiding the Midas Touch: Consequences of Misaligned AI . Some parts of the main text are repeated for completeness. In this section, we formalize the problem presented in the introduction in the context of objective function design for AI agents. If they could simply express the entirety of their preferences to the robot, there would not be value misalignment. Unfortunately, there are many aspects of the world about which the human cares, and it is intractable to enumerate this complete set to the robot.

--This paper introduces OpenLS-DGF, an adaptive logic synthesis dataset generation framework, to enhance machine learning (ML) applications within the logic synthesis process. Previous dataset generation flows were tailored for specific tasks or lacked integrated machine learning capabilities. While OpenLS-DGF supports various machine learning tasks by encapsulating the three fundamental steps of logic synthesis: Boolean representation, logic optimization, and technology mapping. It preserves the original information in both V erilog and machine-learning-friendly GraphML formats. The verilog files offer semi-customizable capabilities, enabling researchers to insert additional steps and incrementally refine the generated dataset. Furthermore, OpenLS-DGF includes an adaptive circuit engine that facilitates the final dataset management and downstream tasks. The generated OpenLS-D-v1 dataset comprises 46 combinational designs from established benchmarks, totaling over 966,000 Boolean circuits. OpenLS-D-v1 supports integrating new data features, making it more versatile for new challenges. This paper demonstrates the versatility of OpenLS-D-v1 through four distinct downstream tasks: circuit classification, circuit ranking, quality of results (QoR) prediction, and probability prediction. Each task is chosen to represent essential steps of logic synthesis, and the experimental results show the generated dataset from OpenLS-DGF achieves prominent diversity and applicability. OGIC synthesis is a key phase in the electronic design automation (EDA) flow of digital circuits, translating high-level specifications into a gate-level netlist. Recently, there has been a trend towards adopting ML approaches for the EDA [1] domain. V arious machine learning methodologies have been proposed, demonstrating improvements in different aspects of the logic synthesis process, including logic optimization [2], [3], [4], [5], [6], technology mapping [7], [8], [9], and formal verification [10], [11]. These machine learning-based techniques have shown their promise in improving the efficiency and quality of logic synthesis steps.

In the logic synthesis stage, structure transformations in the synthesis tool need to be combined into optimization sequences and act on the circuit to meet the specified circuit area and delay. However, logic synthesis optimization sequences are time-consuming to run, and predicting the quality of the results (QoR) against the synthesis optimization sequence for a circuit can help engineers find a better optimization sequence faster. In this work, we propose a deep learning method to predict the QoR of unseen circuit-optimization sequences pairs. Specifically, the structure transformations are translated into vectors by embedding methods and advanced natural language processing (NLP) technology (Transformer) is used to extract the features of the optimization sequences. In addition, to enable the prediction process of the model to be generalized from circuit to circuit, the graph representation of the circuit is represented as an adjacency matrix and a feature matrix. Graph neural networks(GNN) are used to extract the structural features of the circuits. For this problem, the Transformer and three typical GNNs are used. Furthermore, the Transformer and GNNs are adopted as a joint learning policy for the QoR prediction of the unseen circuit-optimization sequences. The methods resulting from the combination of Transformer and GNNs are benchmarked. The experimental results show that the joint learning of Transformer and GraphSage gives the best results. The Mean Absolute Error (MAE) of the predicted result is 0.412.

Solving partial differential equations (PDEs) is a central task in scientific computing. Recently, neural network approximation of PDEs has received increasing attention due to its flexible meshless discretization and its potential for high-dimensional problems. One fundamental numerical difficulty is that random samples in the training set introduce statistical errors into the discretization of loss functional which may become the dominant error in the final approximation, and therefore overshadow the modeling capability of the neural network. In this work, we propose a new minmax formulation to optimize simultaneously the approximate solution, given by a neural network model, and the random samples in the training set, provided by a deep generative model. The key idea is to use a deep generative model to adjust random samples in the training set such that the residual induced by the approximate PDE solution can maintain a smooth profile when it is being minimized. Such an idea is achieved by implicitly embedding the Wasserstein distance between the residual-induced distribution and the uniform distribution into the loss, which is then minimized together with the residual. A nearly uniform residual profile means that its variance is small for any normalized weight function such that the Monte Carlo approximation error of the loss functional is reduced significantly for a certain sample size. The adversarial adaptive sampling (AAS) approach proposed in this work is the first attempt to formulate two essential components, minimizing the residual and seeking the optimal training set, into one minmax objective functional for the neural network approximation of PDEs.

The ever increasing memory requirements of several applications has led to increased demands which might not be met by embedded devices. Constraining the usage of memory in such cases is of paramount importance. It is important that such code size improvements should not have a negative impact on the runtime. Improving the execution time while optimizing for code size is a non-trivial but a significant task. The ordering of standard optimization sequences in modern compilers is fixed, and are heuristically created by the compiler domain experts based on their expertise. However, this ordering is sub-optimal, and does not generalize well across all the cases. We present a reinforcement learning based solution to the phase ordering problem, where the ordering improves both the execution time and code size. We propose two different approaches to model the sequences: one by manual ordering, and other based on a graph called Oz Dependence Graph (ODG). Our approach uses minimal data as training set, and is integrated with LLVM. We show results on x86 and AArch64 architectures on the benchmarks from SPEC-CPU 2006, SPEC-CPU 2017 and MiBench. We observe that the proposed model based on ODG outperforms the current Oz sequence both in terms of size and execution time by 6.19% and 11.99% in SPEC 2017 benchmarks, on an average.

In this paper we introduce Shackleton as a generalized framework enabling the application of linear genetic programming -- a technique under the umbrella of evolutionary algorithms -- to a variety of use cases. We also explore here a novel application for this class of methods: optimizing sequences of LLVM optimization passes. The algorithm underpinning Shackleton is discussed, with an emphasis on the effects of different features unique to the framework when applied to LLVM pass sequences. Combined with analysis of different hyperparameter settings, we report the results on automatically optimizing pass sequences using Shackleton for two software applications at differing complexity levels. Finally, we reflect on the advantages and limitations of our current implementation and lay out a path for further improvements. These improvements aim to surpass hand-crafted solutions with an automatic discovery method for an optimal pass sequence.

The phase-ordering problem of modern compilers has received a lot of attention from the research community over the years, yet remains largely unsolved. Various optimization sequences exposed to the user are manually designed by compiler developers. In designing such a sequence developers have to choose the set of optimization passes, their parameters and ordering within a sequence. Resulting sequences usually fall short of achieving optimal runtime for a given source code and may sometimes even degrade the performance when compared to unoptimized version. In this paper, we employ a deep reinforcement learning approach to the phase-ordering problem. Provided with sub-sequences constituting LLVM's O3 sequence, our agent learns to outperform the O3 sequence on the set of source codes used for training and achieves competitive performance on the validation set, gaining up to 1.32x speedup on previously-unseen programs. Notably, our approach differs from autotuning methods by not depending on one or more test runs of the program for making successful optimization decisions. It has no dependence on any dynamic feature, but only on the statically-attainable intermediate representation of the source code. We believe that the models trained using our approach can be integrated into modern compilers as neural optimization agents, at first to complement, and eventually replace the hand-crafted optimization sequences.