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.

168,695 papers · 148 categories

Trend · papers per month

88175263350 · Jun 202019922001200920172026
48 results for representation harm

Contrastive learning harms minority group representations, affecting downstream tasks.

problem Representation harm in contrastive learning, especially affecting minority groups.
method Causal mediation analysis and stochastic block model explanation.
result Representation harm in contrastive learning is partly responsible for allocation harm in downstream tasks.

Introduces MPR to measure and optimize representation across intersectional groups in retrieval.

problem Harmful stereotypes, cultural erasure, and social disparities in image search and retrieval.
method Develops MPR metric, practical estimation methods, theoretical guarantees, and optimization algorithms.
result Optimizing MPR yields more proportional representation across multiple intersectional groups, often with minimal retrieval accuracy compromise.

Algorithm removes spurious concepts from neural network representations without harming task performance.

problem Spurious correlations hinder neural network out-of-distribution generalization.
method Iterative algorithm that identifies two orthogonal subspaces in neural network representation.
result Algorithm outperforms existing methods on computer vision and natural language processing benchmarks.

COCA refactors training data to identify and erase unsafe concepts in LLMs.

problem Identifying and erasing unsafe concepts in Large Language Models (LLMs) for safety alignment.
method Concept Concentration (COCA) refactors training data with an explicit reasoning process to identify and erase unsafe concepts.
result COCA significantly reduces both in-distribution and out-of-distribution jailbreak success rates while maintaining strong performance on regular tasks.

Proposes a new method to measure and avoid harm in machine learning decisions.

problem Measuring and avoiding harm in machine learning algorithms.
method Formal definition of harm and benefit using causal models, counterfactual objective functions.
result Demonstrates that standard machine learning methods can lead to harmful policies under distributional shifts.

Prediction models can harm patients even when accurate, leading to self-fulfilling prophecies.

problem Prediction models can lead to harmful decisions that worsen patient outcomes.
method Formal characterization of harmful prediction models and analysis of their impact.
result Well-calibrated models are ineffective for decision-making as they do not change the data distribution.

Theorem. Let M be a compact, connected, oriented smooth Riemannian n-manifold with non-empty boundary. Then the cohomology of the complex (Harm*(M),d) of harmonic forms on M is given by the direct sum H^p(Harm*(M),d) = H^p(M;R) + H^(p-1)(M;R) for p=0,1,...,n. When M is a closed manifold, a form is harmonic if and only …

2005-08-19abs ↗pdf ↗

The paper analyzes how deep neural networks handle noisy labels and finds disparate impacts.

problem Disparate impacts of noisy labels on instances with different representation frequencies.
method Quantifying harms, analyzing solutions, and comparing their impacts on different frequency instances.
result Existing solutions lead to disparate treatments, benefiting higher-frequency instances more.

Common fairness definitions in machine learning focus on balancing notions of disparity and utility. In this work, we study fairness in the context of risk disparity among sub-populations. We are interested in learning models that minimize performance discrepancies across sensitive groups without causing unnecessary ha…

2019-11-16abs ↗pdf ↗

Contrastive learning benefits from generated data but can be harmed by it too.

problem Contrastive learning's reliance on data augmentation and the impact of generated data.
method Investigates the role of generated data in contrastive learning and proposes Adaptive Inflation (AdaInf).
result Generated data can sometimes harm contrastive learning, and AdaInf improves performance.

REN addresses uncertainty in user feedbacks for better recommendation systems.

problem Recurrent neural networks focus solely on item relevance, neglecting diverse item exploration.
method Proposes REN, a new type of recurrent neural network that balances relevance and exploration while accounting for representation uncertainty.
result REN achieves satisfactory long-term rewards on synthetic and real-world recommendation datasets, outperforming state-of-the-art models.

The study finds that memorization is necessary or harmful depending on the prior distribution and noise level.

problem The impact of memorization on generalization in overparameterized models.
method An overparameterized linear model with general priors in a Bayesian setup.
result Explicit conditions for optimal generalization based on the prior distribution and noise level.

Contrastive learning outperforms autoencoders and GANs in feature recovery and downstream tasks.

problem Theoretical understanding of contrastive learning's superiority in feature learning.
method Theoretical analysis of contrastive learning in linear representation settings.
result Contrastive learning outperforms autoencoders and GANs for feature recovery and in-domain downstream tasks.

Study characterizes harmful low-fidelity data sources for surrogate models.

problem Identifying which low-fidelity data sources to use in constructing surrogate models.
method Employed benchmark filtering techniques to assess harmful sources using limited data.
result Provided guidelines for using low-fidelity sources in an industrial setting.

Neural Networks are being integrated into safety critical systems, e.g., perception systems for autonomous vehicles, which require trained networks to perform safely in novel scenarios. It is challenging to verify neural networks because their decisions are not explainable, they cannot be exhaustively tested, and finit…

2019-12-20abs ↗pdf ↗

Diffusion LLMs can efficiently generate harmful prompts for adversarial testing.

problem Generating harmful prompts for adversarial testing is resource-intensive and costly.
method Transformed adversarial prompt optimization into an efficient inference task using pretrained Diffusion LLMs.
result Only a few conditional samples are required to generate harmful prompts with high reward.

Detects harmful distribution shifts in deployed models without false alarms.

problem Detecting harmful distribution shifts in deployed models without false alarms.
method Sequential tools for testing if the difference between source and target distributions leads to a significant increase in a risk function.
result Demonstrated the efficacy of the proposed framework through extensive empirical studies.

Selective planning with imperfect models reduces harmful effects of model inadequacy.

problem Harmful effects of using an imperfect model in reinforcement learning.
method Selective planning with heteroscedastic regression to estimate predictive uncertainty from model inadequacy.
result Effective selective planning requires considering both parameter uncertainty and model inadequacy.

New framework removes harmful momentum effect for long-tailed classification.

problem Challenges in maintaining balanced datasets with long-tailed data.
method Causal inference framework to disentangle and remove harmful effects of momentum.
result Achieves state-of-the-art performance on long-tailed visual recognition benchmarks.

Data whitening and second order optimization harm generalization by reducing access to dataset information.

problem Harmful effects of data whitening and second order optimization on generalization in machine learning.
method Analysis of fully connected models and experimental verification.
result Data whitening and second order optimization reduce or prevent generalization by limiting access to dataset information.

Prediction markets can be manipulated by traders who can move contract settlements, harming price discovery.

problem Manipulation of settlement times in prediction markets leads to unfair wealth transfer and harms price discovery.
method Developed a model showing how settlement manipulation transfers wealth and harms price discovery, and observed real-world effects on Polymarket's Bitcoin contract.
result Manipulators capture significant profits from retail traders, especially when settlement times are short.

Lower class selectivity makes networks more robust to natural perturbations but more vulnerable to adversarial attacks.

problem Understanding how class selectivity affects robustness to different types of perturbations in neural networks.
method Investigated the relationship between class selectivity and robustness to natural and adversarial perturbations in neural networks.
result Lower class selectivity increases robustness to natural perturbations but decreases robustness to adversarial attacks.

"Overlearning" means that a model trained for a seemingly simple objective implicitly learns to recognize attributes and concepts that are (1) not part of the learning objective, and (2) sensitive from a privacy or bias perspective. For example, a binary gender classifier of facial images also learns to recognize races…

2019-05-28abs ↗pdf ↗

Ethereum block builders can earn up to $14M/month by reordering transactions, harming users.

problem Block builders can exploit transaction reordering to earn significant profits, harming users.
method Estimation of MEV payments and analysis of reordering effects.
result Block builders can earn up to $14M/month by reordering transactions, skewing the distribution.