arXiv research

A new method for private query release using Johnson-Lindenstrauss projection.

Study private query release with public data, reducing sample sizes.

Noisy Max and Sparse Vector are selection algorithms for differential privacy and serve as building blocks for more complex algorithms. In this paper we show that both algorithms can release additional information for free (i.e., at no additional privacy cost). Noisy Max is used to return the approximate maximizer amon…

Three new oracle-efficient algorithms for private synthetic data release.

In adaptive data analysis, the user makes a sequence of queries on the data, where at each step the choice of query may depend on the results in previous steps. The releases are often randomized in order to reduce overfitting for such adaptively chosen queries. In this paper, we propose a minimax framework for adaptive…

GRAND ensures node-level differential privacy for network data.

We consider accurately answering smooth queries while preserving differential privacy. A query is said to be $K$-smooth if it is specified by a function defined on $[-1,1]^d$ whose partial derivatives up to order $K$ are all bounded. We develop an $ε$-differentially private mechanism for the class of $K$-smooth queries…

Deep neural networks have recently achieved tremendous success in image classification. Recent studies have however shown that they are easily misled into incorrect classification decisions by adversarial examples. Adversaries can even craft attacks by querying the model in black-box settings, where no information abou…

FAQ efficiently evaluates LLMs with statistical guarantees using adaptive query selection.

Among other macroeconomic indicators, the monthly release of U.S. unemployment rate figures in the Employment Situation report by the U.S. Bureau of Labour Statistics gets a lot of media attention and strongly affects the stock markets. I investigate whether a profitable investment strategy can be constructed by predic…

The paper tackles machine unlearning by designing efficient algorithms for adaptive query classes.

A new mechanism for differentially private Fréchet mean on SPD matrices.

Framework purifies approximate differential privacy to pure differential privacy.

We revisit the problem of differentially private release of classification queries. In this problem, the goal is to design an algorithm that can accurately answer a sequence of classification queries based on a private training set while ensuring differential privacy. We formally study this problem in the agnostic PAC …

Semantic code search is the task of retrieving relevant code given a natural language query. While related to other information retrieval tasks, it requires bridging the gap between the language used in code (often abbreviated and highly technical) and natural language more suitable to describe vague concepts and ideas…

Differentially private data structures for estimating distances between strings.

It has recently been observed that neural language models trained on unstructured text can implicitly store and retrieve knowledge using natural language queries. In this short paper, we measure the practical utility of this approach by fine-tuning pre-trained models to answer questions without access to any external c…

Paper introduces data-dependent SSP for private linear and logistic regression.

When translating natural language questions into SQL queries to answer questions from a database, we would like our methods to generalize to domains and database schemas outside of the training set. To handle complex questions and database schemas with a neural encoder-decoder paradigm, it is critical to properly encod…

New framework predicts earnings announcements using press release content, surpassing earnings surprises.

Unify gradients to improve deep networks' robustness against black-box attacks.

Privacy is enhanced by synthetic data release even with unlimited data.

New algorithm maintains privacy while improving model performance in selective release.

A new method for releasing AI workflows to avoid premature incorrect results.

Dialogue State Tracking (DST) is a core component of virtual assistants such as Alexa or Siri. To accomplish various tasks, these assistants need to support an increasing number of services and APIs. The Schema-Guided State Tracking track of the 8th Dialogue System Technology Challenge highlighted the DST problem for u…

Automates phased release strategy to balance risk and speed.

User releases data to service provider while balancing privacy and utility.

To train good supervised and semi-supervised object classifiers, it is critical that we not waste the time of the human experts who are providing the training labels. Existing active learning strategies can have uneven performance, being efficient on some datasets but wasteful on others, or inconsistent just between ru…

Neural network for subgraph similarity computation with pruning.

IPO Finance Agent evaluates LLMs on SpaceX IPO due diligence, surpassing Finance Agent v2.

IPO Finance Agent extends Finance Agent v2 for SpaceX S-1 filings, improving accuracy and cost-efficiency.

Model predicts real-time job applicant numbers for regional economic analysis.

New algorithms improve privacy-preserving data release using external predictions.

We lay theoretical foundations for new database release mechanisms that allow third-parties to construct consistent estimators of population statistics, while ensuring that the privacy of each individual contributing to the database is protected. The proposed framework rests on two main ideas. First, releasing (an esti…

BioFinBERT analyzes sentiment of biotech press releases and financial text around inflection points.

Solves TOD systems' query annotation problem without explicit annotations.

Study exact community recovery in noisy SBM with limited queries.

Proposes a new query autocompletion method that maximizes retrieval performance.

LAZO reduces query complexity and variance in ZO methods.

We consider a query-based data acquisition problem for binary classification of unknown labels, which has diverse applications in communications, crowdsourcing, recommender systems and active learning. To ensure reliable recovery of unknown labels with as few number of queries as possible, we consider an effective quer…

We consider the problem of adaptively PAC-learning a probability distribution $\mathcal{P}$'s mode by querying an oracle for information about a sequence of i.i.d. samples $X_1, X_2, \ldots$ generated from $\mathcal{P}$. We consider two different query models: (a) each query is an index $i$ for which the oracle reveals…

Estimates heavy hitters in data streams with queries, balancing accuracy and efficiency.

Survey of statistical queries and their applications.

We study the query complexity of a learner-private sequential learning problem, motivated by the privacy and security concerns due to eavesdropping that arise in practical applications such as pricing and Federated Learning. A learner tries to estimate an unknown scalar value, by sequentially querying an external datab…

Source coding is the canonical problem of data compression in information theory. In a locally encodable source coding, each compressed bit depends on only few bits of the input. In this paper, we show that a recently popular model of semi-supervised clustering is equivalent to locally encodable source coding. In this …

A new query embedding method improves KB performance on complex queries.

Answering complex logical queries on large-scale incomplete knowledge graphs (KGs) is a fundamental yet challenging task. Recently, a promising approach to this problem has been to embed KG entities as well as the query into a vector space such that entities that answer the query are embedded close to the query. Howeve…

In this paper we study the adaptive learnability of decision trees of depth at most $d$ from membership queries. This has many applications in automated scientific discovery such as drugs development and software update problem. Feldman solves the problem in a randomized polynomial time algorithm that asks $\tilde O(2^…