Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,657 papers · 148 categories

Trend · papers per month

174348521695 · Jun 202019922001200920172026
48 results for trainable influence functions

Paper improves deep learning for solving evolutionary equations with trainable hard constraints.

problem Low computational accuracy of standard PINNs in large temporal domains.
method Sequential learning strategies and trainable influence functions for hard constraints.
result Significantly improved computational accuracy and universality of the method.

This research improves neural network performance with adaptive activation functions in sparse data settings.

problem Limited data availability in scientific and engineering problems.
method Investigation of two types of adaptive activation functions with individual trainable parameters.
result Adaptive activation functions, especially with individual trainable parameters, enhance prediction accuracy and confidence in sparse data settings.

New proof links initial class bias to DNN trainability, challenging traditional understanding.

problem Understanding the initial class bias in DNNs and its impact on trainability.
method Theoretical proof linking initial class bias to mean field theories of DNNs.
result Efficient learning is connected to a network's prejudice towards a specific class, contradicting traditional understanding.

Survey of trainable activation functions in neural networks.

problem Improving neural network performance through trainable activation functions.
method Taxonomy and comparison of recent and past models of trainable activation functions.
result Many trainable activation functions are equivalent to adding neuron layers with fixed activation functions and simple constraints.

Architecture optimization, which is a technique for finding an efficient neural network that meets certain requirements, generally reduces to a set of multiple-choice selection problems among alternative sub-structures or parameters. The discrete nature of the selection problem, however, makes this optimization difficu…

2019-04-24abs ↗pdf ↗

New framework improves interpretability of trainable prompts.

problem Improving task-specific LLM performance with soft prompts remains a black-box method.
method Developed a theoretical framework for evaluating interpretability of trainable prompts, inspired new objective functions.
result Found a fundamental trade-off between interpretability and task performance in trainable prompts.

New method uses trainable activations to make BNNs behave like GPs.

problem Making Bayesian Neural Networks (BNNs) behave like Gaussian Processes (GPs).
method Introduced trainable activations and periodic activations to map GP priors to BNNs. Used 2-Wasserstein distance for optimization.
result Method consistently outperforms existing approaches or matches heuristic methods.

In this paper, we study the trainability of rectified linear unit (ReLU) networks. A ReLU neuron is said to be dead if it only outputs a constant for any input. Two death states of neurons are introduced; tentative and permanent death. A network is then said to be trainable if the number of permanently dead neurons is …

2019-07-23abs ↗pdf ↗

Quantum models face barren plateaus, but specific losses can be trainable.

problem Barren plateaus and loss concentration in quantum generative models.
method Investigated explicit and implicit losses, and their interplay.
result Explicit losses lead to new barren plateaus, while implicit losses can be trainable.

To compare entities of differing types and structural components, the artificial neural network paradigm was used to cross-compare structural components between heterogeneous documents. Trainable weighted structural components were input into machine-learned activation functions of the neurons. The model was used for m…

2018-01-09abs ↗pdf ↗

Connections between nodes of fully connected neural networks are usually represented by weight matrices. In this article, functional transfer matrices are introduced as alternatives to the weight matrices: Instead of using real weights, a functional transfer matrix uses real functions with trainable parameters to repre…

2017-10-28abs ↗pdf ↗

Linearized attention fails to converge to NTK limit even at large widths.

problem Understanding the convergence of attention mechanisms to the kernel regime.
method Analyzes linearized attention and its relationship to the NTK limit, considering practical widths and conditions.
result Linearized attention does not converge to its NTK limit at any practical width, revealing a fundamental trade-off.

Many neural speech enhancement and source separation systems operate in the time-frequency domain. Such models often benefit from making their Short-Time Fourier Transform (STFT) front-ends trainable. In current literature, these are implemented as large Discrete Fourier Transform matrices; which are prohibitively inef…

2020-02-20abs ↗pdf ↗

This work explores the relation between trainability and dequantization in variational QML models.

problem Understanding the interplay between trainability and dequantization in variational QML models.
method Provide precise definitions of trainability and dequantization, study their relation, and introduce recipes for building PQC-based QML models.
result Identify conditions under which trainability and non-dequantization are not mutually exclusive.

In the context of learning to map an input II to a function hI:XRh_I:\mathcal{X}\to \mathbb{R}, two alternative methods are compared: (i) an embedding-based method, which learns a fixed function in which II is encoded as a conditioning signal e(I)e(I) and the learned function takes the form hI(x)=q(x,e(I))h_I(x) = q(x,e(I)), and (ii) …

2020-02-23abs ↗pdf ↗

Influence functions are inaccurate in deep learning models, especially for deeper networks.

problem Inaccuracies in influence functions in deep learning models.
method Empirical study of influence functions in neural network models trained on various datasets.
result Influence estimates are often erroneous for deeper networks and require regularization.

RelatIF selects more intuitive training examples for explaining model predictions.

problem Influence functions identify outliers as explanatory examples, leading to poor explanations.
method RelatIF separates global and local influence, optimizing for local relative to global effects.
result Examples selected by RelatIF are more intuitive than those from influence functions.

Establishes statistical and computational bounds for influence diagnostics.

problem Identifying influential datapoints or subsets in machine learning models.
method Finite-sample statistical bounds and computational complexity for influence functions and approximate maximum influence perturbations.
result Established statistical and computational guarantees for influence diagnostics.

Influence functions help study large language model generalization, revealing surprising decay patterns.

problem Understanding and mitigating risks in large language models (LLMs).
method Eigenvalue-corrected Kronecker-Factored Approximation (EK-FAC) to scale influence functions to LLMs.
result Influences decay to near-zero when key phrases order is flipped, revealing a surprising limitation.

New research investigates why influence functions are fragile and proposes new validation procedures.

problem Understanding and mitigating the fragility of influence functions in deep learning model explanations.
method Verification of influence functions using various conditions and procedures, including convexity and non-convexity.
result Validation procedures may cause the observed fragility of influence functions.

Study shows influence functions are poor for neural networks but useful for identifying influential examples.

problem Influence functions misalign with leave-one-out retraining in neural networks.
method Decomposed the discrepancy into five terms and studied their contributions across different architectures and datasets.
result Influence functions are a good approximation to the proximal Bregman response function (PBRF), useful for identifying influential examples.

The paper extends influence functions to sequence tagging tasks for better model interpretability.

problem Lack of interpretability methods for sequence tagging models.
method Define and compute influence of training instance segments on test segment predictions.
result The segment influence method tracks with true influence and identifies annotation errors.

Predicts trainability of deep neural networks using reconstruction entropy.

problem Predicting the initial conditions for trainability of deep neural networks.
method Cascade of auxiliary networks to reconstruct input from activation layers, computing relative entropy.
result Predicts trainability of deep feedforward networks on various datasets with a single epoch.

Better Hessian approximations improve influence function attributions in deep learning.

problem Influence functions are difficult to compute due to ill-conditioned Hessians, leading to poor data attribution performance.
method Investigated the impact of Hessian approximation quality on influence-function attributions in a controlled setting.
result Better Hessian approximations consistently yield better influence score quality.

The paper simplifies influence computations for large-scale machine learning models.

problem Improving training efficiency and accuracy in large-scale models.
method Study influence functions, define memorization, simplify computations.
result Influence functions can be practical for large-scale models, indicating memorization.

PatchGT uses non-trainable graph patches to improve graph representation learning.

problem Learning high-level information in graph tasks with direct Transformer models.
method PatchGT segments graphs into non-trainable patches, uses GNN for patch-level learning, and Transformer for graph-level learning.
result PatchGT achieves higher expressiveness and competitive performance on benchmark datasets.

NEON uses neural networks to optimize functions in infinite-dimensional spaces.

problem Optimizing composite functions in function spaces.
method NEON (Neural Epistemic Operator Networks) for sequential decision-making.
result NEON achieves state-of-the-art performance with fewer parameters.

New IF method improves accuracy in deep neural networks with noisy data.

problem Inaccurate influence estimates in deep neural networks, especially with noisy data.
method Established a connection between influence estimation error, validation set risk, and sharpness, introducing a novel estimation form for flat validation minima.
result Our novel Influence Function approach provides more accurate influence estimates, validated across various tasks.

A new method, VIF, calculates influence for non-decomposable losses efficiently.

problem Efficiently calculating influence for complex machine learning models with non-decomposable losses.
method Revisiting influence function from robust statistics, proposing Versatile Influence Function (VIF) for any non-decomposable loss.
result VIF method is up to 10^3 times faster than brute-force methods and closely matches influence results.

Quantum machine learning faces challenges similar to variational quantum algorithms in training.

problem Challenges in training quantum machine learning models.
method Bridge between variational quantum algorithms and quantum machine learning, applying gradient scaling results.
result Gradient scaling results for variational quantum algorithms can also be applied to quantum machine learning models, revealing new trainability issues.

Quantum ML promises faster data analysis but faces trainability challenges.

problem Challenges in training quantum machine learning models.
method Review of current methods and applications of quantum neural networks and quantum deep learning.
result Opportunities for quantum advantage in quantum machine learning.

How can we explain the predictions of a black-box model? In this paper, we use influence functions -- a classic technique from robust statistics -- to trace a model's prediction through the learning algorithm and back to its training data, thereby identifying training points most responsible for a given prediction. To …

2017-03-14abs ↗pdf ↗

Paper presents a new way to estimate model changes without full model evaluation.

problem Efficiently estimating changes in model parameters and outputs due to data point removal.
method Dual representation of influence functions for linearizable models, reducing computational complexity.
result The dual representation can be an efficient alternative to original influence functions, especially for large models.

This study proposes a trainable adaptive window switching (AWS) method and apply it to a deep-neural-network (DNN) for speech enhancement in the modified discrete cosine transform domain. Time-frequency (T-F) mask processing in the short-time Fourier transform (STFT)-domain is a typical speech enhancement method. To re…

2018-11-05abs ↗pdf ↗

With the rapid adoption of machine learning systems in sensitive applications, there is an increasing need to make black-box models explainable. Often we want to identify an influential group of training samples in a particular test prediction for a given machine learning model. Existing influence functions tackle this…

2019-11-01abs ↗pdf ↗