arXiv subjects

Vladimir Gusev

Publications and source records attributed to Vladimir Gusev.

11 recordsLinked to original sources

arXiv2026

Fractal KV-Cache Archives: Lossless Symbolic Storage with In-Place Retrieval for Long-Context LLM Inference

The key-value (KV) cache dominates the memory cost of long-context autoregressive inference, and a growing body of work compresses it through quantization, eviction, or offloading. We study a complementary question: once a position's KV state has been quantized to codebook indices, how should the resulting symbol stream be stored, and can the storage layer do more than store? A family of contractive iterated-map codes that serialize a symbol sequence into a sequence of low-dimensional real vectors is revisited, and it is shown that they form a natural archive format for a quantized KV cache with the following features. The method provides exactly the access pattern a growing cache requires. It is lossless, it runs in linear time, and supports O(1) random access and O(1) amortized append. A controlled study of the quantizer feeding this archive is conducted on GPT-2 with 1024-token contexts. Keeping a small exact window (4 attention sinks plus 32 recent tokens) and archiving the rest, per-head residual vector quantization reduces the archived cache by 36-54x relative to an fp16 cache at a perplexity cost of 11-15%, and we quantify a sharp key/value asymmetry - quantizing keys is roughly 4x more damaging than quantizing values, consistent with prior low-bit KV work - and use it to allocate bits in a hybrid scheme. Finally, we show the archive is simultaneously a search index: approximate substring queries execute directly on the stored vectors, and matched context is decoded from the matched vector without ever materializing the surrounding text. We further characterize the archive's operating range: truncating stored points yields a lossy regime whose distortion we localize, and probability-weighting the maps recovers arithmetic coding, exposing a trade-off between rate efficiency, random access, and memory. We release all code; every number reproduces on a laptop CPU.

cs.LG↗

arXiv2024

Assessing data-driven predictions of band gap and electrical conductivity for transparent conducting materials

Machine Learning (ML) has offered innovative perspectives for accelerating the discovery of new functional materials, leveraging the increasing availability of material databases. Despite the promising advances, data-driven methods face constraints imposed by the quantity and quality of available data. Moreover, ML is often employed in tandem with simulated datasets originating from density functional theory (DFT), and assessed through in-sample evaluation schemes. This scenario raises questions about the practical utility of ML in uncovering new and significant material classes for industrial applications. Here, we propose a data-driven framework aimed at accelerating the discovery of new transparent conducting materials (TCMs), an important category of semiconductors with a wide range of applications. To mitigate the shortage of available data, we create and validate unique experimental databases, comprising several examples of existing TCMs. We assess state-of-the-art (SOTA) ML models for property prediction from the stoichiometry alone. We propose a bespoke evaluation scheme to provide empirical evidence on the ability of ML to uncover new, previously unseen materials of interest. We test our approach on a list of 55 compositions containing typical elements of known TCMs. Although our study indicates that ML tends to identify new TCMs compositionally similar to those in the training data, we empirically demonstrate that it can highlight material candidates that may have been previously overlooked, offering a systematic approach to identify materials that are likely to display TCMs characteristics.

cond-mat.mtrl-sci↗

arXiv2023

Cluster Exploration using Informative Manifold Projections

Dimensionality reduction (DR) is one of the key tools for the visual exploration of high-dimensional data and uncovering its cluster structure in two- or three-dimensional spaces. The vast majority of DR methods in the literature do not take into account any prior knowledge a practitioner may have regarding the dataset under consideration. We propose a novel method to generate informative embeddings which not only factor out the structure associated with different kinds of prior knowledge but also aim to reveal any remaining underlying structure. To achieve this, we employ a linear combination of two objectives: firstly, contrastive PCA that discounts the structure associated with the prior information, and secondly, kurtosis projection pursuit which ensures meaningful data separation in the obtained embeddings. We formulate this task as a manifold optimization problem and validate it empirically across a variety of datasets considering three distinct types of prior knowledge. Lastly, we provide an automated framework to perform iterative visual exploration of high-dimensional data.

cs.LG↗

arXiv2023

Metrics for quantifying isotropy in high dimensional unsupervised clustering tasks in a materials context

Clustering is a common task in machine learning, but clusters of unlabelled data can be hard to quantify. The application of clustering algorithms in chemistry is often dependant on material representation. Ascertaining the effects of different representations, clustering algorithms, or data transformations on the resulting clusters is difficult due to the dimensionality of these data. We present a thorough analysis of measures for isotropy of a cluster, including a novel implantation based on an existing derivation. Using fractional anisotropy, a common method used in medical imaging for comparison, we then expand these measures to examine the average isotropy of a set of clusters. A use case for such measures is demonstrated by quantifying the effects of kernel approximation functions on different representations of the Inorganic Crystal Structure Database. Broader applicability of these methods is demonstrated in analysing learnt embedding of the MNIST dataset. Random clusters are explored to examine the differences between isotropy measures presented, and to see how each method scales with the dimensionality. Python implementations of these measures are provided for use by the community.

cs.LG↗

arXiv2023

First Order Methods for Geometric Optimization of Crystal Structures

The geometric optimization of crystal structures is a procedure widely used in Chemistry that changes the geometrical placement of the particles inside a structure. It is called structural relaxation and constitutes a local minimization problem with a non-convex objective function whose domain complexity increases according to the number of particles involved. In this work we study the performance of the two most popular first order optimization methods in structural relaxation. Although frequently employed, there is a lack of their study in this context from an algorithmic point of view. We run each algorithm in combination with a constant step size, which provides a benchmark for the methods' analysis and direct comparison. We also design dynamic step size rules and study how these improve the two algorithms' performance. Our results show that there is a trade-off between convergence rate and the possibility of an experiment to succeed, hence we construct a function to assign utility to each method based on our respective preference. The function is built according to a recently introduced model of preference indication concerning algorithms with deadline and their run time. Finally, building on all our insights from the experimental results, we provide algorithmic recipes that best correspond to each of the presented preferences and select one recipe as the optimal for equally weighted preferences. Alongside our results we present our open source Python software veltiCRYS, which was used to perform the geometric optimization experiments. Our implementation, can be easily edited to accommodate other energy functions and is especially targeted for testing different methods in structural relaxation.

math.OC↗

arXiv2023

Element selection for functional materials discovery by integrated machine learning of elemental contributions to properties

Fundamental differences between materials originate from the unique nature of their constituent chemical elements. Before specific differences emerge according to the precise ratios of elements in a given crystal structure, a material can be represented by the set of its constituent chemical elements. By working at the level of the periodic table, assessment of materials at the level of their phase fields reduces the combinatorial complexity to accelerate screening, and circumvents the challenges associated with composition-level approaches such as poor extrapolation within phase fields, and the impossibility of exhaustive sampling. This early stage discrimination combined with evaluation of novelty of phase fields aligns with the outstanding experimental challenge of identifying new areas of chemistry to investigate, by prioritising which elements to combine in a reaction. Here, we demonstrate that phase fields can be assessed with respect to the maximum expected value of a target functional property and ranked according to chemical novelty. We develop and present PhaseSelect, an end-to-end machine learning model that combines the representation, classification, regression and ranking of phase fields. First, PhaseSelect constructs elemental characteristics from the co-occurrence of chemical elements in computationally and experimentally reported materials, then it employs attention mechanisms to learn representation for phase fields and assess their functional performance. At the level of the periodic table, PhaseSelect quantifies the probability of observing a functional property, estimates its value within a phase field and also ranks a phase field novelty, which we demonstrate with significant accuracy for three avenues of materials applications for high-temperature superconductivity, high-temperature magnetism, and targeted bandgap energy.

cond-mat.mtrl-sci↗

arXiv2022

Random projections and Kernelised Leave One Cluster Out Cross-Validation: Universal baselines and evaluation tools for supervised machine learning for materials properties

With machine learning being a popular topic in current computational materials science literature, creating representations for compounds has become common place. These representations are rarely compared, as evaluating their performance - and the performance of the algorithms that they are used with - is non-trivial. With many materials datasets containing bias and skew caused by the research process, leave one cluster out cross validation (LOCO-CV) has been introduced as a way of measuring the performance of an algorithm in predicting previously unseen groups of materials. This raises the question of the impact, and control, of the range of cluster sizes on the LOCO-CV measurement outcomes. We present a thorough comparison between composition-based representations, and investigate how kernel approximation functions can be used to better separate data to enhance LOCO-CV applications. We find that domain knowledge does not improve machine learning performance in most tasks tested, with band gap prediction being the notable exception. We also find that the radial basis function improves the linear separability of chemical datasets in all 10 datasets tested and provide a framework for the application of this function in the LOCO-CV process to improve the outcome of LOCO-CV measurements regardless of machine learning algorithm, choice of metric, and choice of compound representation. We recommend kernelised LOCO-CV as a training paradigm for those looking to measure the extrapolatory power of an algorithm on materials data.

cs.LG↗

arXiv2022

On the Hardness of Energy Minimisation for Crystal Structure Prediction

Crystal Structure Prediction (csp) is one of the central and most challenging problems in materials science and computational chemistry. In csp, the goal is to find a configuration of ions in 3D space that yields the lowest potential energy. Finding an efficient procedure to solve this complex optimisation question is a well known open problem. Due to the exponentially large search space, the problem has been referred in several materials-science papers as "NP-Hard and very challenging" without a formal proof. This paper fills a gap in the literature providing the first set of formally proven NP-Hardness results for a variant of csp with various realistic constraints. In particular, we focus on the problem of removal: the goal is to find a substructure with minimal potential energy, by removing a subset of the ions. Our main contributions are NP-Hardness results for the csp removal problem, new embeddings of combinatorial graph problems into geometrical settings, and a more systematic exploration of the energy function to reveal the complexity of csp. In a wider context, our results contribute to the analysis of computational problems for weighted graphs embedded into the three-dimensional Euclidean space.

cs.CC↗

arXiv2020

Crystal Structure Prediction via Oblivious Local Search

We study Crystal Structure Prediction, one of the major problems in computational chemistry. This is essentially a continuous optimization problem, where many different, simple and sophisticated, methods have been proposed and applied. The simple searching techniques are easy to understand, usually easy to implement, but they can be slow in practice. On the other hand, the more sophisticated approaches perform well in general, however almost all of them have a large number of parameters that require fine tuning and, in the majority of the cases, chemical expertise is needed in order to properly set them up. In addition, due to the chemical expertise involved in the parameter-tuning, these approaches can be {\em biased} towards previously-known crystal structures. Our contribution is twofold. Firstly, we formalize the Crystal Structure Prediction problem, alongside several other intermediate problems, from a theoretical computer science perspective. Secondly, we propose an oblivious algorithm for Crystal Structure Prediction that is based on local search. Oblivious means that our algorithm requires minimal knowledge about the composition we are trying to compute a crystal structure for. In addition, our algorithm can be used as an intermediate step by {\em any} method. Our experiments show that our algorithms outperform the standard basin hopping, a well studied algorithm for the problem.

cs.CE↗

arXiv2018

Personal Names Popularity Estimation and its Application to Record Linkage

This study deals with a fairly simply formulated problem -- how to estimate the number of people bearing the same full name in a large population. Estimation of name popularity can leverage personal name matching in databases and be of interest for many other domains. A distinctive feature of large collections of names is that they contain a large number of unique items, which is challenging for statistical modeling. We investigate a number of statistical techniques and also propose a simple yet effective method aimed at obtaining more accurate count estimates. In our experiments we use a dataset containing about 20 million name occurrences that correspond to about 13 million real-world persons. We perform a thorough evaluation of the name count estimation methods and a record linkage experiment guided by name popularity estimates. Obtained results suggest that theoretically informed approaches outperform simple heuristics and can be useful in a variety of applications.

cs.DB↗

arXiv2017

On the interplay between Babai and Cerny's conjectures

Motivated by the Babai conjecture and the Cerny conjecture, we study the reset thresholds of automata with the transition monoid equal to the full monoid of transformations of the state set. For automata with $n$ states in this class, we prove that the reset thresholds are upper-bounded by $2n^2-6n+5$ and can attain the value $\tfrac{n(n-1)}{2}$. In addition, we study diameters of the pair digraphs of permutation automata and construct $n$-state permutation automata with diameter $\tfrac{n^2}{4} + o(n^2)$.

cs.FL↗