The performance of Large Language Models has achieved superhuman breadth with unprecedented depth. At the same time, the language models are mostly black box models and the underlying mechanisms for performance have been evaluated using synthetic or mechanistic schemes. We extend current mechanistic schemes to incorporate Logic, memory, and nuances of Language such as latent structure. The proposed framework is called LOLAMEME and we provide two instantiations of LOLAMEME: LoLa and MeMe languages. We then consider two generative language model architectures: transformer-based GPT-2 and convolution-based Hyena. We propose the hybrid architecture T HEX and use LOLAMEME framework is used to compare three architectures. T HEX outperforms GPT-2 and Hyena on select tasks.

Amid the increasing interest in the deployment of Distributed Energy Resources (DERs), the Virtual Power Plant (VPP) has emerged as a pivotal tool for aggregating diverse DERs and facilitating their participation in wholesale energy markets. These VPP deployments have been fueled by the Federal Energy Regulatory Commission's Order 2222, which makes DERs and VPPs competitive across market segments. However, the diversity and decentralized nature of DERs present significant challenges to the scalable coordination of VPP assets. To address efficiency and speed bottlenecks, this paper presents a novel machine learning-assisted distributed optimization to coordinate VPP assets. Our method, named LOOP-MAC(Learning to Optimize the Optimization Process for Multi-agent Coordination), adopts a multi-agent coordination perspective where each VPP agent manages multiple DERs and utilizes neural network approximators to expedite the solution search. The LOOP-MAC method employs a gauge map to guarantee strict compliance with local constraints, effectively reducing the need for additional post-processing steps. Our results highlight the advantages of LOOP-MAC, showcasing accelerated solution times per iteration and significantly reduced convergence times. The LOOP-MAC method outperforms conventional centralized and distributed optimization methods in optimization tasks that require repetitive and sequential execution.

The issue with machine learning pipelines is that they need to pass state from one step to another. When this works, it's a beautiful thing to behold. When it doesn't, well, it's not pretty, and I think the clip below sums this up pretty well. Azure ML Pipelines are no stranger to this need for passing data between steps, so you have a variety of options at your disposal. This means it's not always easy to find the best one, and I've often seen people confused when trying to pick the best option.

The 1956 paper The Magical Number Seven, Plus or Minus Two is the most widely cited paper in the 126 year history of the journal Psychological Review. The author George A. Miller is considered one of the founders in the field of cognitive science. His historic claim is that you can only juggle between 5 and 9 things in your brain at any one time. To my knowledge, despite some controversy over the years, this 7 2 figure has withstood the ongoing reproducibility crisis and it appears to capture a deep truth about how our brains actually function. Many people are skeptical of the claim because seven sounds like an absurdly small number, surely if you are doing something complex like writing software, or planning a wedding for that matter, you are juggling dozens to hundreds of things?

Weighted Logic is a powerful tool for the specification of calculations over semirings that depend on qualitative information. Using a novel combination of Weighted Logic and Here-and-There (HT) Logic, in which this dependence is based on intuitionistic grounds, we introduce Answer Set Programming with Algebraic Constraints (ASP(A C)), where rules may contain constraints that compare semiring values to weighted formula evaluations. Such constraints provide streamlined access to a manifold of constructs available in ASP, like aggregates, choice constraints, and arithmetic operators. They extend some of them and provide a generic framework for defining programs with algebraic computation, which can be fruitfully used e.g. for provenance semantics of datalog programs. While undecidable in general, expressive fragments of ASP(A C) can be exploited for effective problem solving in a rich framework. This work is under consideration for acceptance in Theory and Practice of Logic Programming.

The simplified parse tree (SPT) presented in Aroma, a state-of-the-art code recommendation system, is a tree-structured representation used to infer code semantics by capturing program \emph{structure} rather than program \emph{syntax}. This is a departure from the classical abstract syntax tree, which is principally driven by programming language syntax. While we believe a semantics-driven representation is desirable, the specifics of an SPT's construction can impact its performance. We analyze these nuances and present a new tree structure, heavily influenced by Aroma's SPT, called a \emph{context-aware parse tree} (CAPT). CAPT enhances SPT by providing a richer level of semantic representation. Specifically, CAPT provides additional binding support for language-specific techniques for adding semantically-salient features, and language-agnostic techniques for removing syntactically-present but semantically-irrelevant features. Our research quantitatively demonstrates the value of our proposed semantically-salient features, enabling a specific CAPT configuration to be 39\% more accurate than SPT across the 48,610 programs we analyzed.

The main benefits of using R compared to other languages are speed and handling of large data sets. That's the cause why we started the implementation of pricing models for one of our customers in R in 2010. Today, this customer runs a shiny server with eight shiny applications for more than 500 users. Image 1 depicts the architecture of the shiny applications and internal and external interfaces. The initial R script used different data sets to run mathematical models (cluster analysis and regression models) to evaluate a fair market value for surplus spare parts.

The code in this repository provides a framework for solving arbitrary separable convex optimization problems with Alternating Direction Method of Multipliers (ADMM). Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers. The framework is built over Spark and is generic: to apply it to an arbitrary separable convex problem, a developer needs to implement only three functions (one that reads data from a file, one that evaluates the objective function, and one that solves a local optimization problem with an additional proximal penalty term). An example implementation of logistic regression is included in the code. Updated spark installation instructions can be found here.