Searcharxiv⌕ Search

arXiv subjects

Mark Coates

Publications and source records attributed to Mark Coates.

At least 37 records · Page 2Linked to original sources
arXiv2025

Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in LLMs

Large language models (LLMs) have rapidly progressed into general-purpose agents capable of solving a broad spectrum of tasks. However, current models remain inefficient at reasoning: they apply fixed inference-time compute regardless of task complexity, often overthinking simple problems while underthinking hard ones. This survey presents a comprehensive review of efficient test-time compute (TTC) strategies, which aim to improve the computational efficiency of LLM reasoning. We introduce a two-tiered taxonomy that distinguishes between L1-controllability, methods that operate under fixed compute budgets, and L2-adaptiveness, methods that dynamically scale inference based on input difficulty or model confidence. We benchmark leading proprietary LLMs across diverse datasets, highlighting critical trade-offs between reasoning performance and token usage. Compared to prior surveys on efficient reasoning, our review emphasizes the practical control, adaptability, and scalability of TTC methods. Finally, we discuss emerging trends such as hybrid thinking models and identify key challenges for future work towards making LLMs more computationally efficient, robust, and responsive to user constraints.

cs.AI↗
arXiv2025

SKOLR: Structured Koopman Operator Linear RNN for Time-Series Forecasting

Koopman operator theory provides a framework for nonlinear dynamical system analysis and time-series forecasting by mapping dynamics to a space of real-valued measurement functions, enabling a linear operator representation. Despite the advantage of linearity, the operator is generally infinite-dimensional. Therefore, the objective is to learn measurement functions that yield a tractable finite-dimensional Koopman operator approximation. In this work, we establish a connection between Koopman operator approximation and linear Recurrent Neural Networks (RNNs), which have recently demonstrated remarkable success in sequence modeling. We show that by considering an extended state consisting of lagged observations, we can establish an equivalence between a structured Koopman operator and linear RNN updates. Building on this connection, we present SKOLR, which integrates a learnable spectral decomposition of the input signal with a multilayer perceptron (MLP) as the measurement functions and implements a structured Koopman operator via a highly parallel linear RNN stack. Numerical experiments on various forecasting benchmarks and dynamical systems show that this streamlined, Koopman-theory-based design delivers exceptional performance.

cs.LG↗
arXiv2025

Differentially private and decentralized randomized power method

The randomized power method has gained significant interest due to its simplicity and efficient handling of large-scale spectral analysis and recommendation tasks. However, its application to large datasets containing personal information (e.g., web interactions, search history, personal tastes) raises critical privacy problems. This paper addresses these issues by proposing enhanced privacy-preserving variants of the method. First, we propose a variant that reduces the amount of the noise required in current techniques to achieve Differential Privacy (DP). More precisely, we refine the privacy analysis so that the Gaussian noise variance no longer grows linearly with the target rank, achieving the same DP guarantees with strictly less noise. Second, we adapt our method to a decentralized framework in which data is distributed among multiple users. The decentralized protocol strengthens privacy guarantees with no accuracy penalty and a low computational and communication overhead. Our results include the provision of tighter convergence bounds for both the centralized and decentralized versions, and an empirical comparison with previous work using real recommendation datasets.

cs.LG↗
arXiv2025

Half Search Space is All You Need

Neural Architecture Search (NAS) is a powerful tool for automating architecture design. One-Shot NAS techniques, such as DARTS, have gained substantial popularity due to their combination of search efficiency with simplicity of implementation. By design, One-Shot methods have high GPU memory requirements during the search. To mitigate this issue, we propose to prune the search space in an efficient automatic manner to reduce memory consumption and search time while preserving the search accuracy. Specifically, we utilise Zero-Shot NAS to efficiently remove low-performing architectures from the search space before applying One-Shot NAS to the pruned search space. Experimental results on the DARTS search space show that our approach reduces memory consumption by 81% compared to the baseline One-Shot setup while achieving the same level of accuracy.

cs.LG↗
arXiv2025

Refining Answer Distributions for Improved Large Language Model Reasoning

Large Language Models (LLMs) have exhibited an impressive capability to perform reasoning tasks, especially if they are encouraged to generate a sequence of intermediate steps. Reasoning performance can be improved by suitably combining multiple LLM responses, generated either in parallel in a single query, or via sequential interactions with LLMs throughout the reasoning process. Existing strategies for combination, such as self-consistency and progressive-hint-prompting, make inefficient usage of the LLM responses. We present Refined Answer Distributions, a novel and principled algorithmic framework to enhance the reasoning capabilities of LLMs. Our approach can be viewed as an iterative sampling strategy for forming a Monte Carlo approximation of an underlying distribution of answers, with the goal of identifying the mode -- the most likely answer. Empirical evaluation on several reasoning benchmarks demonstrates the superiority of the proposed approach.

cs.CL↗
arXiv2025

MODL: Multilearner Online Deep Learning

Online deep learning tackles the challenge of learning from data streams by balancing two competing goals: fast learning and deep learning. However, existing research primarily emphasizes deep learning solutions, which are more adept at handling the ``deep'' aspect than the ``fast'' aspect of online learning. In this work, we introduce an alternative paradigm through a hybrid multilearner approach. We begin by developing a fast online logistic regression learner, which operates without relying on backpropagation. It leverages closed-form recursive updates of model parameters, efficiently addressing the fast learning component of the online learning challenge. This approach is further integrated with a cascaded multilearner design, where shallow and deep learners are co-trained in a cooperative, synergistic manner to solve the online learning problem. We demonstrate that this approach achieves state-of-the-art performance on standard online learning datasets. We make our code available: https://github.com/AntonValk/MODL

cs.LG↗
arXiv2025

Sparse Decomposition of Graph Neural Networks

Graph Neural Networks (GNN) exhibit superior performance in graph representation learning, but their inference cost can be high, due to an aggregation operation that can require a memory fetch for a very large number of nodes. This inference cost is the major obstacle to deploying GNN models with \emph{online prediction} to reflect the potentially dynamic node features. To address this, we propose an approach to reduce the number of nodes that are included during aggregation. We achieve this through a sparse decomposition, learning to approximate node representations using a weighted sum of linearly transformed features of a carefully selected subset of nodes within the extended neighbourhood. The approach achieves linear complexity with respect to the average node degree and the number of layers in the graph neural network. We introduce an algorithm to compute the optimal parameters for the sparse decomposition, ensuring an accurate approximation of the original GNN model, and present effective strategies to reduce the training time and improve the learning process. We demonstrate via extensive experiments that our method outperforms other baselines designed for inference speedup, achieving significant accuracy gains with comparable inference times for both node classification and spatio-temporal forecasting tasks.

cs.LG↗
arXiv2025

Variation Matters: from Mitigating to Embracing Zero-Shot NAS Ranking Function Variation

Neural Architecture Search (NAS) is a powerful automatic alternative to manual design of a neural network. In the zero-shot version, a fast ranking function is used to compare architectures without training them. The outputs of the ranking functions often vary significantly due to different sources of randomness, including the evaluated architecture's weights' initialization or the batch of data used for calculations. A common approach to addressing the variation is to average a ranking function output over several evaluations. We propose taking into account the variation in a different manner, by viewing the ranking function output as a random variable representing a proxy performance metric. During the search process, we strive to construct a stochastic ordering of the performance metrics to determine the best architecture. Our experiments show that the proposed stochastic ordering can effectively boost performance of a search on standard benchmark search spaces.

cs.LG↗
arXiv2025

Personalized Negative Reservoir for Incremental Learning in Recommender Systems

Recommender systems have become an integral part of online platforms. Every day the volume of training data is expanding and the number of user interactions is constantly increasing. The exploration of larger and more expressive models has become a necessary pursuit to improve user experience. However, this progression carries with it an increased computational burden. In commercial settings, once a recommendation system model has been trained and deployed it typically needs to be updated frequently as new client data arrive. Cumulatively, the mounting volume of data is guaranteed to eventually make full batch retraining of the model from scratch computationally infeasible. Naively fine-tuning solely on the new data runs into the well-documented problem of catastrophic forgetting. Despite the fact that negative sampling is a crucial part of training with implicit feedback, no specialized technique exists that is tailored to the incremental learning framework. In this work, we propose a personalized negative reservoir strategy, which is used to obtain negative samples for the standard triplet loss of graph-based recommendation systems. Our technique balances alleviation of forgetting with plasticity by encouraging the model to remember stable user preferences and selectively forget when user interests change. We derive the mathematical formulation of a negative sampler to populate and update the reservoir. We integrate our design in three SOTA and commonly used incremental recommendation models. We show that these concrete realizations of our negative reservoir framework achieve state-of-the-art results for standard benchmarks using multiple top-k evaluation metrics.

cs.IR↗
arXiv2025

InnerThoughts: Disentangling Representations and Predictions in Large Language Models

Large language models (LLMs) contain substantial factual knowledge which is commonly elicited by multiple-choice question-answering prompts. Internally, such models process the prompt through multiple transformer layers, building varying representations of the problem within its hidden states. Ultimately, however, only the hidden state corresponding to the final layer and token position are used to predict the answer label. In this work, we propose instead to learn a small separate neural network predictor module on a collection of training questions, that take the hidden states from all the layers at the last temporal position as input and outputs predictions. In effect, such a framework disentangles the representational abilities of LLMs from their predictive abilities. On a collection of hard benchmarks, our method achieves considerable improvements in performance, sometimes comparable to supervised fine-tuning procedures, but at a fraction of the computational cost.

cs.CL↗
arXiv2025

Secure Federated Graph-Filtering for Recommender Systems

Recommender systems often rely on graph-based filters, such as normalized item-item adjacency matrices and low-pass filters. While effective, the centralized computation of these components raises concerns about privacy, security, and the ethical use of user data. This work proposes two decentralized frameworks for securely computing these critical graph components without centralizing sensitive information. The first approach leverages lightweight Multi-Party Computation and distributed singular vector computations to privately compute key graph filters. The second extends this framework by incorporating low-rank approximations, enabling a trade-off between communication efficiency and predictive performance. Empirical evaluations on benchmark datasets demonstrate that the proposed methods achieve comparable accuracy to centralized state-of-the-art systems while ensuring data confidentiality and maintaining low communication costs. Our results highlight the potential for privacy-preserving decentralized architectures to bridge the gap between utility and user data protection in modern recommender systems.

cs.IR↗
arXiv2024

Enhancing Logical Reasoning in Large Language Models through Graph-based Synthetic Data

Despite recent advances in training and prompting strategies for Large Language Models (LLMs), these models continue to face challenges with complex logical reasoning tasks that involve long reasoning chains. In this work, we explore the potential and limitations of using graph-based synthetic reasoning data as training signals to enhance LLMs' reasoning capabilities. Our extensive experiments, conducted on two established natural language reasoning tasks -- inductive reasoning and spatial reasoning -- demonstrate that supervised fine-tuning (SFT) with synthetic graph-based reasoning data effectively enhances LLMs' reasoning performance without compromising their effectiveness on other standard evaluation benchmarks.

cs.CL↗
arXiv2024

Graph Knowledge Distillation to Mixture of Experts

In terms of accuracy, Graph Neural Networks (GNNs) are the best architectural choice for the node classification task. Their drawback in real-world deployment is the latency that emerges from the neighbourhood processing operation. One solution to the latency issue is to perform knowledge distillation from a trained GNN to a Multi-Layer Perceptron (MLP), where the MLP processes only the features of the node being classified (and possibly some pre-computed structural information). However, the performance of such MLPs in both transductive and inductive settings remains inconsistent for existing knowledge distillation techniques. We propose to address the performance concerns by using a specially-designed student model instead of an MLP. Our model, named Routing-by-Memory (RbM), is a form of Mixture-of-Experts (MoE), with a design that enforces expert specialization. By encouraging each expert to specialize on a certain region on the hidden representation space, we demonstrate experimentally that it is possible to derive considerably more consistent performance across multiple datasets. Code available at https://github.com/Rufaim/routing-by-memory.

cs.LG↗
arXiv2024

Enhancing CTR Prediction in Recommendation Domain with Search Query Representation

Many platforms, such as e-commerce websites, offer both search and recommendation services simultaneously to better meet users' diverse needs. Recommendation services suggest items based on user preferences, while search services allow users to search for items before providing recommendations. Since users and items are often shared between the search and recommendation domains, there is a valuable opportunity to enhance the recommendation domain by leveraging user preferences extracted from the search domain. Existing approaches either overlook the shift in user intention between these domains or fail to capture the significant impact of learning from users' search queries on understanding their interests. In this paper, we propose a framework that learns from user search query embeddings within the context of user preferences in the recommendation domain. Specifically, user search query sequences from the search domain are used to predict the items users will click at the next time point in the recommendation domain. Additionally, the relationship between queries and items is explored through contrastive learning. To address issues of data sparsity, the diffusion model is incorporated to infer positive items the user will select after searching with certain queries in a denoising manner, which is particularly effective in preventing false positives. Effectively extracting this information, the queries are integrated into click-through rate prediction in the recommendation domain. Experimental analysis demonstrates that our model outperforms state-of-the-art models in the recommendation domain.

cs.IR↗
arXiv2024

Dynamic layer selection in decoder-only transformers

The vast size of Large Language Models (LLMs) has prompted a search to optimize inference. One effective approach is dynamic inference, which adapts the architecture to the sample-at-hand to reduce the overall computational cost. We empirically examine two common dynamic inference methods for natural language generation (NLG): layer skipping and early exiting. We find that a pre-trained decoder-only model is significantly more robust to layer removal via layer skipping, as opposed to early exit. We demonstrate the difficulty of using hidden state information to adapt computation on a per-token basis for layer skipping. Finally, we show that dynamic computation allocation on a per-sequence basis holds promise for significant efficiency gains by constructing an oracle controller. Remarkably, we find that there exists an allocation which achieves equal performance to the full model using only 23.3% of its layers on average.

cs.CL↗
arXiv2024

HardCore Generation: Generating Hard UNSAT Problems for Data Augmentation

Efficiently determining the satisfiability of a boolean equation -- known as the SAT problem for brevity -- is crucial in various industrial problems. Recently, the advent of deep learning methods has introduced significant potential for enhancing SAT solving. However, a major barrier to the advancement of this field has been the scarcity of large, realistic datasets. The majority of current public datasets are either randomly generated or extremely limited, containing only a few examples from unrelated problem families. These datasets are inadequate for meaningful training of deep learning methods. In light of this, researchers have started exploring generative techniques to create data that more accurately reflect SAT problems encountered in practical situations. These methods have so far suffered from either the inability to produce challenging SAT problems or time-scalability obstacles. In this paper we address both by identifying and manipulating the key contributors to a problem's ``hardness'', known as cores. Although some previous work has addressed cores, the time costs are unacceptably high due to the expense of traditional heuristic core detection techniques. We introduce a fast core detection procedure that uses a graph neural network. Our empirical results demonstrate that we can efficiently generate problems that remain hard to solve and retain key attributes of the original example problems. We show via experiment that the generated synthetic SAT problems can be used in a data augmentation setting to provide improved prediction of solver runtimes.

cs.LG↗
arXiv2024

Interacting Diffusion Processes for Event Sequence Forecasting

Neural Temporal Point Processes (TPPs) have emerged as the primary framework for predicting sequences of events that occur at irregular time intervals, but their sequential nature can hamper performance for long-horizon forecasts. To address this, we introduce a novel approach that incorporates a diffusion generative model. The model facilitates sequence-to-sequence prediction, allowing multi-step predictions based on historical event sequences. In contrast to previous approaches, our model directly learns the joint probability distribution of types and inter-arrival times for multiple events. This allows us to fully leverage the high dimensional modeling capability of modern generative models. Our model is composed of two diffusion processes, one for the time intervals and one for the event types. These processes interact through their respective denoising functions, which can take as input intermediate representations from both processes, allowing the model to learn complex interactions. We demonstrate that our proposal outperforms state-of-the-art baselines for long-horizon forecasting of TPP.

cs.LG↗
arXiv2024

Predicting Probabilities of Error to Combine Quantization and Early Exiting: QuEE

Machine learning models can solve complex tasks but often require significant computational resources during inference. This has led to the development of various post-training computation reduction methods that tackle this issue in different ways, such as quantization which reduces the precision of weights and arithmetic operations, and dynamic networks which adapt computation to the sample at hand. In this work, we propose a more general dynamic network that can combine both quantization and early exit dynamic network: QuEE. Our algorithm can be seen as a form of soft early exiting or input-dependent compression. Rather than a binary decision between exiting or continuing, we introduce the possibility of continuing with reduced computation. This complicates the traditionally considered early exiting problem, which we solve through a principled formulation. The crucial factor of our approach is accurate prediction of the potential accuracy improvement achievable through further computation. We demonstrate the effectiveness of our method through empirical evaluation, as well as exploring the conditions for its success on 4 classification datasets.

cs.LG↗