The Lottery Ticket Hypothesis (LTH) suggests there exists a sparse LTH mask and weights that achieve the same generalization performance as the dense model while using significantly fewer parameters. However, finding a LTH solution is computationally expensive, and a LTH sparsity mask does not generalize to other random weight initializations. Recent work has suggested that neural networks trained from random initialization find solutions within the same basin modulo permutation, and proposes a method to align trained models within the same loss basin. We hypothesize that misalignment of basins is the reason why LTH masks do not generalize to new random initializations and propose permuting the LTH mask to align with the new optimization basin when performing sparse training from a different random init. We empirically show a significant increase in generalization when sparse training from random initialization with the permuted mask as compared to using the non-permuted LTH mask, on multiple datasets (CIFAR-10/100 & ImageNet) and models (VGG11 & ResNet20/50).

In top-down enumeration for program synthesis, abstraction-based pruning uses an abstract domain to approximate the set of possible values that a partial program, when completed, can output on a given input. If the set does not contain the desired output, the partial program and all its possible completions can be pruned. In its general form, abstraction-based pruning requires manually designed, domain-specific abstract domains and semantics, and thus has only been used in domain-specific synthesizers. This paper provides sufficient conditions under which a form of abstraction-based pruning can be automated for arbitrary synthesis problems in the general-purpose Semantics-Guided Synthesis (SemGuS) framework without requiring manually-defined abstract domains. We show that if the semantics of the language for which we are synthesizing programs exhibits some monotonicity properties, one can obtain an abstract interval-based semantics for free from the concrete semantics of the programming language, and use such semantics to effectively prune the search space. We also identify a condition that ensures such abstract semantics can be used to compute a precise abstraction of the set of values that a program derivable from a given hole in a partial program can produce. These precise abstractions make abstraction-based pruning more effective. We implement our approach in a tool, M oito , which can tackle synthesis problems defined in the SemGuS framework. M oito can automate interval-based pruning without any a-priori knowledge of the problem domain, and solve synthesis problems that previously required domain-specific, abstraction-based synthesizers—e.g., synthesis of regular expressions, CSV file schema, and imperative programs from examples.

A monitor is a widely-used concurrent programming abstraction that encapsulates all shared state between threads. Monitors can be classified as being either implicit or explicit depending on the primitives they provide. Implicit monitors are much easier to program but typically not as efficient. To address this gap, there has been recent research on automatically synthesizing explicit-signal monitors from an implicit specification, but prior work does not exploit all paralellization opportunities due to the use of a single lock for the entire monitor. This paper presents a new technique for synthesizing fine-grained explicit-synchronization protocols from implicit monitors. Our method is based on two key innovations: First, we present a new static analysis for inferring safe interleavings that allow violating mutual exclusion of monitor operations without changing its semantics. Second, we use the results of this static analysis to generate a MaxSAT instance whose models correspond to correct-by-construction synchronization protocols. We have implemented our approach in a tool called Cortado and evaluate it on monitors that contain parallelization opportunities. Our evaluation shows that Cortado can synthesize synchronization policies that are competitive with, or even better than, expert-written ones on these benchmarks.

The increasing influence and adoption of Additive Manufacturing (AM) technology across manufacturing sectors has made it a target for cyber-physical attacks. While several techniques have been developed to mitigate specific AM related threats, there is little research aimed at assessing cyber-physical threats or vulnerabilities that extend across the entire AM workflow. Such an assessment requires a holistic approach that systematically analyzes all components of the AM workflow for cyber-physical vulnerabilities. Several methodologies have been successfully applied towards identifying such vulnerabilities in other domains like Information Technology (IT) systems. In response, this paper provides a systems approach towards identifying cyber-physical vulnerabilities in AM systems using the Vulnerability Assessment and Mitigation (VAM) methodology. This approach characterizes the different vulnerabilities that arise from specific AM threats by identifying the quality attributes of the AM system that introduces it. The security techniques developed to mitigate these threats are reduced to a combination of fundamental mitigation techniques, that have been compiled based on its success in other domains. Using the resources from the VAM methodology, fundamental mitigation techniques that are best suited towards mitigating specific vulnerability attributes are identified. Comparing the combination of fundamental mitigation techniques associated with an AM security technique and the list of fundamental mitigation techniques suggested by the VAM methodology provides insight into how an AM security technique can be improved. Finally, the paper provides a case study of the proposed adapted VAM methodology to demonstrate its application.

Distributed devices in smart grid systems are decentralized and connected to the power grid through different types of equipment transmit, which will produce numerous energy losses when power flows from one bus to another. One of the most efficient approaches to reduce energy losses is to integrate distributed generations (DGs), mostly renewable energy sources. However, the uncertainty of DG may cause instability issues. Additionally, due to the similar consumption habits of customers, the peak load period of power consumption may cause congestion in the power grid and affect the energy delivery. Energy management with DG regulation is considered to be one of the most efficient solutions for solving these instability issues. In this paper, we consider a power system with both distributed generators and customers, and propose a distributed locational marginal pricing (DLMP)-based unified energy management system (uEMS) model, which, unlike previous works, considers both increasing profit benefits for DGs and increasing stability of the distributed power system (DPS). The model contains two parts: 1) a game theory-based loss reduction allocation (LRA); and 2) a load feedback control (LFC) with price elasticity. In the former component, we develop an iterative loss reduction method using DLMP to remunerate DGs for their participation in energy loss reduction. By using iterative LRA to calculate energy loss reduction, the model accurately rewards DG contribution and offers a fair competitive market. Furthermore, the overall profit of all DGs is maximized by utilizing game theory to calculate an optimal LRA scheme for calculating the distributed loss of every DG in each time slot. In the latter component of the model, we propose an LFC submodel with price elasticity, where a DLMP feedback signal is calculated by customer demand to regulate peak-load value. In uEMS, LFC first determines the DLMP signal of a customer bus by a time-shift load optimization (LO) algorithm based on the changes of customer demand, which is fed back to the DLMP of the customer bus at the next slot-time, allowing for peak-load regulation via price elasticity. Results based on the IEEE 37-bus feeder system show that the proposed uEMS model can increase DG benefits and improve system stability.

Statistical circuit simulation is exhibiting increasing importance for circuit design under process variations. Existing approaches cannot efficiently analyze the failure probability for circuits with a large number of variation, nor handle problems with multiple disjoint failure regions. The proposed rare event microscope (REscope) first reduces the problem dimension by pruning the parameters with little contribution to circuit failure. Furthermore, we applied a nonlinear classifier which is capable of identifying multiple disjoint failure regions. In REscope, only likely-to-fail samples are simulated then matched to a generalized pareto distribution. On a 108-dimension charge pump circuit in PLL design, REscope outperforms the importance sampling and achieves more than 2 orders of magnitude speedup compared to Monte Carlo. Moreover, it accurately estimates failure rate, while the importance sampling totally fails because failure regions are not correctly captured.