arXiv subjects

Abhishek Gupta

Publications and source records attributed to Abhishek Gupta.

At least 217 records · Page 12Linked to original sources

arXiv2020

Green Lighting ML: Confidentiality, Integrity, and Availability of Machine Learning Systems in Deployment

Security and ethics are both core to ensuring that a machine learning system can be trusted. In production machine learning, there is generally a hand-off from those who build a model to those who deploy a model. In this hand-off, the engineers responsible for model deployment are often not privy to the details of the model and thus, the potential vulnerabilities associated with its usage, exposure, or compromise. Techniques such as model theft, model inversion, or model misuse may not be considered in model deployment, and so it is incumbent upon data scientists and machine learning engineers to understand these potential risks so they can communicate them to the engineers deploying and hosting their models. This is an open problem in the machine learning community and in order to help alleviate this issue, automated systems for validating privacy and security of models need to be developed, which will help to lower the burden of implementing these hand-offs and increasing the ubiquity of their adoption.

cs.CY↗

arXiv2020

Response by the Montreal AI Ethics Institute to the Santa Clara Principles on Transparency and Accountability in Online Content Moderation

In April 2020, the Electronic Frontier Foundation (EFF) publicly called for comments on expanding and improving the Santa Clara Principles on Transparency and Accountability (SCP), originally published in May 2018. The Montreal AI Ethics Institute (MAIEI) responded to this call by drafting a set of recommendations based on insights and analysis by the MAIEI staff and supplemented by workshop contributions from the AI Ethics community convened during two online public consultation workshops. In its submission, MAIEI provides 12 overarching recommendations for the SCP, these include: 1) ensure there is more diversity in the content moderation process; 2) increase transparency into how platforms guide content-ranking; 3) disclose anonymized data on the training and/or cultural background of the content moderators for a platform; 4) tailor content moderation tools for specific issues; 5) draft specific guidelines for messaging applications with regards to data protection in content moderation; 6) take into account cultural differences relevant to what constitutes acceptable behavior online; 7) ensure platforms are transparent in regards to political advertising; 8) ensure greater transparency into the user-generated flagging/reporting systems deployed by a platform; 9) clarify if user content is flagged or reported through an automated system; 10) provide more data on the types of content removed from platforms; 11) provide clear guidelines on the appeal process, as well as data on prior appeals; 12) create a system for periodically revisiting the SCP so it reflects various technological advancements, modifications in law and policy, as well as changing trends or movements in content moderation.

cs.CY↗

arXiv2020

The State of AI Ethics Report (June 2020)

These past few months have been especially challenging, and the deployment of technology in ways hitherto untested at an unrivalled pace has left the internet and technology watchers aghast. Artificial intelligence has become the byword for technological progress and is being used in everything from helping us combat the COVID-19 pandemic to nudging our attention in different directions as we all spend increasingly larger amounts of time online. It has never been more important that we keep a sharp eye out on the development of this field and how it is shaping our society and interactions with each other. With this inaugural edition of the State of AI Ethics we hope to bring forward the most important developments that caught our attention at the Montreal AI Ethics Institute this past quarter. Our goal is to help you navigate this ever-evolving field swiftly and allow you and your organization to make informed decisions. This pulse-check for the state of discourse, research, and development is geared towards researchers and practitioners alike who are making decisions on behalf of their organizations in considering the societal impacts of AI-enabled solutions. We cover a wide set of areas in this report spanning Agency and Responsibility, Security and Risk, Disinformation, Jobs and Labor, the Future of AI Ethics, and more. Our staff has worked tirelessly over the past quarter surfacing signal from the noise so that you are equipped with the right tools and knowledge to confidently tread this complex yet consequential domain.

cs.CY↗

arXiv2020

Ecological Reinforcement Learning

Much of the current work on reinforcement learning studies episodic settings, where the agent is reset between trials to an initial state distribution, often with well-shaped reward functions. Non-episodic settings, where the agent must learn through continuous interaction with the world without resets, and where the agent receives only delayed and sparse reward signals, is substantially more difficult, but arguably more realistic considering real-world environments do not present the learner with a convenient "reset mechanism" and easy reward shaping. In this paper, instead of studying algorithmic improvements that can address such non-episodic and sparse reward settings, we instead study the kinds of environment properties that can make learning under such conditions easier. Understanding how properties of the environment impact the performance of reinforcement learning agents can help us to structure our tasks in ways that make learning tractable. We first discuss what we term "environment shaping" -- modifications to the environment that provide an alternative to reward shaping, and may be easier to implement. We then discuss an even simpler property that we refer to as "dynamism," which describes the degree to which the environment changes independent of the agent's actions and can be measured by environment transition entropy. Surprisingly, we find that even this property can substantially alleviate the challenges associated with non-episodic RL in sparse reward settings. We provide an empirical evaluation on a set of new tasks focused on non-episodic learning with sparse rewards. Through this study, we hope to shift the focus of the community towards analyzing how properties of the environment can affect learning and the ultimate type of behavior that is learned via RL.

cs.LG↗

arXiv2020

Response by the Montreal AI Ethics Institute to the European Commission's Whitepaper on AI

In February 2020, the European Commission (EC) published a white paper entitled, On Artificial Intelligence - A European approach to excellence and trust. This paper outlines the EC's policy options for the promotion and adoption of artificial intelligence (AI) in the European Union. The Montreal AI Ethics Institute (MAIEI) reviewed this paper and published a response addressing the EC's plans to build an "ecosystem of excellence" and an "ecosystem of trust," as well as the safety and liability implications of AI, the internet of things (IoT), and robotics. MAIEI provides 15 recommendations in relation to the sections outlined above, including: 1) focus efforts on the research and innovation community, member states, and the private sector; 2) create alignment between trading partners' policies and EU policies; 3) analyze the gaps in the ecosystem between theoretical frameworks and approaches to building trustworthy AI; 4) focus on coordination and policy alignment; 5) focus on mechanisms that promote private and secure sharing of data; 6) create a network of AI research excellence centres to strengthen the research and innovation community; 7) promote knowledge transfer and develop AI expertise through Digital Innovation Hubs; 8) add nuance to the discussion regarding the opacity of AI systems; 9) create a process for individuals to appeal an AI system's decision or output; 10) implement new rules and strengthen existing regulations; 11) ban the use of facial recognition technology; 12) hold all AI systems to similar standards and compulsory requirements; 13) ensure biometric identification systems fulfill the purpose for which they are implemented; 14) implement a voluntary labelling system for systems that are not considered high-risk; 15) appoint individuals to the oversight process who understand AI systems well and are able to communicate potential risks.

cs.CY↗

arXiv2020

The Social Contract for AI

Like any technology, AI systems come with inherent risks and potential benefits. It comes with potential disruption of established norms and methods of work, societal impacts and externalities. One may think of the adoption of technology as a form of social contract, which may evolve or fluctuate in time, scale, and impact. It is important to keep in mind that for AI, meeting the expectations of this social contract is critical, because recklessly driving the adoption and implementation of unsafe, irresponsible, or unethical AI systems may trigger serious backlash against industry and academia involved which could take decades to resolve, if not actually seriously harm society. For the purpose of this paper, we consider that a social contract arises when there is sufficient consensus within society to adopt and implement this new technology. As such, to enable a social contract to arise for the adoption and implementation of AI, developing: 1) A socially accepted purpose, through 2) A safe and responsible method, with 3) A socially aware level of risk involved, for 4) A socially beneficial outcome, is key.

cs.CY↗

arXiv2020

Response to Office of the Privacy Commissioner of Canada Consultation Proposals pertaining to amendments to PIPEDA relative to Artificial Intelligence

In February 2020, the Montreal AI Ethics Institute (MAIEI) was invited by the Office of the Privacy Commissioner of Canada (OPCC) to provide for comments both at a closed roundtable and in writing on the OPCC consultation proposal for amendments relative to Artificial Intelligence (AI), to the Canadian privacy legislation, the Personal Information Protection and Electronic Documents Act (PIPEDA). The present document includes MAIEI comments and recommendations in writing. Per MAIEI's mission and mandate to act as a catalyst for public feedback pertaining to AI Ethics and regulatory technology developments, as well as to provide for public competence-building workshops on critical topics in such domains, the reader will also find such public feedback and propositions by Montrealers who participated at MAIEI's workshops, submitted as Schedule 1 to the present report. For each of OPCC 12 proposals, and underlying questions, as described on its website, MAIEI provides a short reply, a summary list of recommendations, as well as comments relevant to the question at hand. We leave you with three general statements to keep in mind while going through the next pages: 1) AI systems should be used to augment human capacity for meaningful and purposeful connections and associations, not as a substitute for trust. 2) Humans have collectively accepted to uphold the rule of law, but for machines, the code is rule. Where socio-technical systems are deployed to make important decisions, profiles or inferences about individuals, we will increasingly have to attempt the difficult exercise of drafting and encoding our law in a manner learnable by machines. 3) Let us work collectively towards a world where Responsible AI becomes the rule, before our socio-technical systems become "too connected to fail".

cs.CY↗

arXiv2020

Montreal AI Ethics Institute's Response to Scotland's AI Strategy

In January and February 2020, the Scottish Government released two documents for review by the public regarding their artificial intelligence (AI) strategy. The Montreal AI Ethics Institute (MAIEI) reviewed these documents and published a response on 4 June 2020. MAIEI's response examines several questions that touch on the proposed definition of AI; the people-centered nature of the strategy; considerations to ensure that everyone benefits from AI; the strategy's overarching vision; Scotland's AI ecosystem; the proposed strategic themes; and how to grow public confidence in AI by building responsible and ethical systems. In addition to examining the points above, MAIEI suggests that the strategy be extended to include considerations on biometric data and how that will be processed and used in the context of AI. It also highlights the importance of tackling head-on the inherently stochastic nature of deep learning systems and developing concrete guidelines to ensure that these systems are built responsibly and ethically, particularly as machine learning becomes more accessible. Finally, it concludes that any national AI strategy must clearly address the measurements of success in regards to the strategy's stated goals and vision to ensure that they are interpreted and applied consistently. To do this, there must be inclusion and transparency between those building the systems and those using them in their work.

cs.CY↗

arXiv2020

Unified Characterization Platform for Emerging NVM Technology: Neural Network Application Benchmarking Using off-the-shelf NVM Chips

In this paper, we present a unified FPGA based electrical test-bench for characterizing different emerging NonVolatile Memory (NVM) chips. In particular, we present detailed electrical characterization and benchmarking of multiple commercially available, off-the-shelf, NVM chips viz.: MRAM, FeRAM, CBRAM, and ReRAM. We investigate important NVM parameters such as: (i) current consumption patterns, (ii) endurance, and (iii) error characterization. The proposed FPGA based testbench is then utilized for a Proof-of-Concept (PoC) Neural Network (NN) image classification application. Four emerging NVM chips are benchmarked against standard SRAM and Flash technology for the AI application as active weight memory during inference mode.

cs.AR↗

arXiv2020

Road Grade Estimation Using Crowd-Sourced Smartphone Data

Estimates of road grade/slope can add another dimension of information to existing 2D digital road maps. Integration of road grade information will widen the scope of digital map's applications, which is primarily used for navigation, by enabling driving safety and efficiency applications such as Advanced Driver Assistance Systems (ADAS), eco-driving, etc. The huge scale and dynamic nature of road networks make sensing road grade a challenging task. Traditional methods oftentimes suffer from limited scalability and update frequency, as well as poor sensing accuracy. To overcome these problems, we propose a cost-effective and scalable road grade estimation framework using sensor data from smartphones. Based on our understanding of the error characteristics of smartphone sensors, we intelligently combine data from accelerometer, gyroscope and vehicle speed data from OBD-II/smartphone's GPS to estimate road grade. To improve accuracy and robustness of the system, the estimations of road grade from multiple sources/vehicles are crowd-sourced to compensate for the effects of varying quality of sensor data from different sources. Extensive experimental evaluation on a test route of ~9km demonstrates the superior performance of our proposed method, achieving $5\times$ improvement on road grade estimation accuracy over baselines, with 90\% of errors below 0.3$^\circ$.

eess.SP↗

arXiv2020

Participatory Design to build better contact- and proximity-tracing apps

With the push for contact- and proximity-tracing solutions as a means to manage the spread of the pandemic, there is a distrust between the citizens and authorities that are deploying these solutions. The efficacy of the solutions relies on meeting a minimum uptake threshold which is hitting a barrier because of a lack of trust and transparency in how these solutions are being developed. We propose participatory design as a mechanism to evoke trust and explore how it might be applied to co-create technological solutions that not only meet the needs of the users better but also expand their reach to underserved and high-risk communities. We also highlight the role of the bazaar model of development and complement that with quantitative and qualitative metrics for evaluating the solutions and convincing policymakers and other stakeholders in the value of this approach with empirical evidence.

cs.CY↗

arXiv2020

Mean velocity scaling in plane turbulent wall jets

Studies in the literature on plane turbulent wall jets on flat surfaces, have invariably considered either the nozzle initial conditions or the asymptotic conditions far downstream, as scaling parameters for the streamwise variations of length and velocity scales. These choices, however, do not square with the notion of self similarity which is essentially a "local" concept. We first demonstrate that the streamwise variations of velocity and length scales in wall jets show remarkable scaling with local parameters i.e. there appear to be no imposed length and velocity scales. Next, it is shown that the mean velocity profile data suggest existence of two distinct layers - the wall (inner) layer and the full-free jet (outer) layer. Each of these layers scales on the appropriate length and velocity scales and this scaling is observed to be universal i.e. independent of the local friction Reynolds number. Analysis shows that the overlap of these universal scalings leads to a Reynolds-number-dependent power-law velocity variation in the overlap layer. It is observed that the mean-velocity overlap layer corresponds well to the momentum-balance mesolayer and there appears to be no evidence for an inertial overlap; only the meso-overlap is observed. Introduction of an intermediate variable absorbs the Reynolds-number dependence of the length scale in the overlap layer and this leads to a universal power-law overlap profile for mean velocity in terms of the intermediate variable.

physics.flu-dyn↗

arXiv2020

Unsupervised Meta-Learning for Reinforcement Learning

Meta-learning algorithms use past experience to learn to quickly solve new tasks. In the context of reinforcement learning, meta-learning algorithms acquire reinforcement learning procedures to solve new problems more efficiently by utilizing experience from prior tasks. The performance of meta-learning algorithms depends on the tasks available for meta-training: in the same way that supervised learning generalizes best to test points drawn from the same distribution as the training points, meta-learning methods generalize best to tasks from the same distribution as the meta-training tasks. In effect, meta-reinforcement learning offloads the design burden from algorithm design to task design. If we can automate the process of task design as well, we can devise a meta-learning algorithm that is truly automated. In this work, we take a step in this direction, proposing a family of unsupervised meta-learning algorithms for reinforcement learning. We motivate and describe a general recipe for unsupervised meta-reinforcement learning, and present an instantiation of this approach. Our conceptual and theoretical contributions consist of formulating the unsupervised meta-reinforcement learning problem and describing how task proposals based on mutual information can be used to train optimal meta-learners. Our experimental results indicate that unsupervised meta-reinforcement learning effectively acquires accelerated reinforcement learning procedures without the need for manual task design and these procedures exceed the performance of learning from scratch.

cs.LG↗

arXiv2020

The Ingredients of Real-World Robotic Reinforcement Learning

The success of reinforcement learning for real world robotics has been, in many cases limited to instrumented laboratory scenarios, often requiring arduous human effort and oversight to enable continuous learning. In this work, we discuss the elements that are needed for a robotic learning system that can continually and autonomously improve with data collected in the real world. We propose a particular instantiation of such a system, using dexterous manipulation as our case study. Subsequently, we investigate a number of challenges that come up when learning without instrumentation. In such settings, learning must be feasible without manually designed resets, using only on-board perception, and without hand-engineered reward functions. We propose simple and scalable solutions to these challenges, and then demonstrate the efficacy of our proposed system on a set of dexterous robotic manipulation tasks, providing an in-depth analysis of the challenges associated with this learning paradigm. We demonstrate that our complete system can learn without any human intervention, acquiring a variety of vision-based skills with a real-world three-fingered hand. Results and videos can be found at https://sites.google.com/view/realworld-rl/

cs.LG↗

arXiv2020

Coverage Improvement of Wireless Sensor Networks via Spatial Profile Information

This paper considers a wireless sensor network deployed to sense an environment variable with a known spatial statistical profile. We propose to use the additional information of the spatial profile to improve the sensing range of sensors while allowing some tolerance in their sensing accuracy. We show that the use of this information improves the sensing performance of the total WSN. For this, we first derive analytical expressions for various performance metrics to measure the improvement in the sensing performance of WSN. We then discuss the sensing gains quantitatively using numerical results.

cs.IT↗

arXiv2020

Steady-state fluctuations of a genetic feedback loop with fluctuating rate parameters using the unified colored noise approximation

A common model of stochastic auto-regulatory gene expression describes promoter switching via cooperative protein binding, effective protein production in the active state and dilution of proteins. Here we consider an extension of this model whereby colored noise with a short correlation time is added to the reaction rate parameters -- we show that when the size and timescale of the noise is appropriately chosen it accounts for fast reactions that are not explicitly modelled, e.g., in models with no mRNA description, fluctuations in the protein production rate can account for rapid multiple stages of nuclear mRNA processing which precede translation in eukaryotes. We show how the unified colored noise approximation can be used to derive expressions for the protein number distribution that is in good agreement with stochastic simulations. We find that even when the noise in the rate parameters is small, the protein distributions predicted by our model can be significantly different than models assuming constant reaction rates.

q-bio.SC↗

arXiv2020

DisCor: Corrective Feedback in Reinforcement Learning via Distribution Correction

Deep reinforcement learning can learn effective policies for a wide range of tasks, but is notoriously difficult to use due to instability and sensitivity to hyperparameters. The reasons for this remain unclear. When using standard supervised methods (e.g., for bandits), on-policy data collection provides "hard negatives" that correct the model in precisely those states and actions that the policy is likely to visit. We call this phenomenon "corrective feedback." We show that bootstrapping-based Q-learning algorithms do not necessarily benefit from this corrective feedback, and training on the experience collected by the algorithm is not sufficient to correct errors in the Q-function. In fact, Q-learning and related methods can exhibit pathological interactions between the distribution of experience collected by the agent and the policy induced by training on that experience, leading to potential instability, sub-optimal convergence, and poor results when learning from noisy, sparse or delayed rewards. We demonstrate the existence of this problem, both theoretically and empirically. We then show that a specific correction to the data distribution can mitigate this issue. Based on these observations, we propose a new algorithm, DisCor, which computes an approximation to this optimal distribution and uses it to re-weight the transitions used for training, resulting in substantial improvements in a range of challenging RL settings, such as multi-task learning and learning from noisy reward signals. Blog post presenting a summary of this work is available at: https://bair.berkeley.edu/blog/2020/03/16/discor/.

cs.LG↗

arXiv2020

Reciprocal Collision Avoidance for General Nonlinear Agents using Reinforcement Learning

Finding feasible and collision-free paths for multiple nonlinear agents is challenging in the decentralized scenarios due to limited available information of other agents and complex dynamics constraints. In this paper, we propose a fast multi-agent collision avoidance algorithm for general nonlinear agents with continuous action space, where each agent observes only positions and velocities of nearby agents. To reduce online computation, we first decompose the multi-agent scenario and solve a two agents collision avoidance problem using reinforcement learning (RL). When extending the trained policy to a multi-agent problem, safety is ensured by introducing the optimal reciprocal collision avoidance (ORCA) as linear constraints and the overall collision avoidance action could be found through simple convex optimization. Most existing RL-based multi-agent collision avoidance algorithms rely on the direct control of agent velocities. In sharp contrasts, our approach is applicable to general nonlinear agents. Realistic simulations based on nonlinear bicycle agent models are performed with various challenging scenarios, indicating a competitive performance of the proposed method in avoiding collisions, congestion and deadlock with smooth trajectories.

cs.RO↗