Share this page!

Enter URL or ID to Unroll

You can paste full URL like: https://x.com/threadreaderapp/status/1644127596119195649
or just the ID like: 1644127596119195649

How to get URL link on X (Twitter) App

  1. On the Twitter thread, click on or icon on the bottom
  2. Click again on or Share Via icon
  3. Click on Copy Link to Tweet
  4. Paste it above and click "Unroll Thread"!
  5. More info at Twitter Help
𝙷𝚒𝚖𝚊 𝙻𝚊𝚔𝚔𝚊𝚛𝚊𝚓𝚞 Profile picture
@hima_lakkaraju
Jul 15, 2020 • 6 tweets • 2 min read • Read on X
Want to generate black box explanations that are more stable and are robust to distribution shifts? Our latest #ICML2020 paper provides a generic framework that can be used to generate robust local/global linear/rule-based explanations.
Paper: proceedings.icml.cc/static/paper_f…. Thread ↓ Image
Many existing explanation techniques are highly sensitive even to small changes in data. This results in: 1) incorrect and unstable explanations, (ii) explanations of the same model may differ based on the dataset used to construct them.
To address the above shortcomings, we propose a framework based on adversarial training. We propose and optimize a minimax objective that aims to construct explanations with highest fidelity over a set of possible distribution shifts.
This paper makes one of the first attempts at outlining and tackling the problem of handling distribution shifts in the context of model explanations.
We will be at #ICML2020 to discuss this work tomorrow 7/15

Slot 1: 8am to 845am ET / 7am to 745am CT / 5am to 545am PT / 12am to 1245am AoE
Slot 2: 11pm to 1145pm ET / 10pm to 1045pm CT / 8pm to 845pm PT / 3pm to 345pm AoE

Link: icml.cc/virtual/2020/p…
@trustworthy_ml above thread ↑on our icml paper

• • •

Missing some Tweet in this thread? You can try to force a refresh
　

Keep Current with 𝙷𝚒𝚖𝚊 𝙻𝚊𝚔𝚔𝚊𝚛𝚊𝚓𝚞

𝙷𝚒𝚖𝚊 𝙻𝚊𝚔𝚔𝚊𝚛𝚊𝚓𝚞 Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @hima_lakkaraju

𝙷𝚒𝚖𝚊 𝙻𝚊𝚔𝚔𝚊𝚛𝚊𝚓𝚞 Profile picture
Apr 12
As we increasingly rely on #LLMs for product recommendations and searches, can companies game these models to enhance the visibility of their products?

Our latest work provides answers to this question & demonstrates that LLMs can be manipulated to boost product visibility!

Joint work with @AounonK. More details👇 [1/N]https://arxiv.org/abs/2404.07981
@AounonK @harvard_data @Harvard @D3Harvard @trustworthy_ml LLMs have become ubiquitous, and we are all increasingly relying on them for searches, product information, and recommendations. Given this, we ask a critical question for the first time: Can LLMs be manipulated by companies to enhance the visibility of their products? [2/N]
This question has huge implications for businesses: the ability to manipulate LLMs to enhance product visibility gives vendors a considerable competitive advantage and has the potential to disrupt fair market competition [3/N]
Read 14 tweets
𝙷𝚒𝚖𝚊 𝙻𝚊𝚔𝚔𝚊𝚛𝚊𝚓𝚞 Profile picture
May 2, 2023
Regulating #AI is important, but it can also be quite challenging in practice. Our #ICML2023 paper highlights the tensions between Right to Explanation & Right to be Forgotten, and proposes the first algorithmic framework to address these tensions arxiv.org/pdf/2302.04288… [1/N] Image
@SatyaIsIntoLLMs @Jiaqi_Ma_ Multiple regulatory frameworks (e.g., GDPR, CCPA) were introduced in recent years to regulate AI. Several of these frameworks emphasized the importance of enforcing two key principles ("Right to Explanation" and "Right to be Forgotten") in order to effectively regulate AI [2/N]
While Right to Explanation ensures that individuals who are adversely impacted by algorithmic outcomes are provided with an actionable explanation, Right to be Forgotten allows individuals to request erasure of their personal data from databases/models of an organization [3/N]
Read 14 tweets
𝙷𝚒𝚖𝚊 𝙻𝚊𝚔𝚔𝚊𝚛𝚊𝚓𝚞 Profile picture
Nov 26, 2022
Our group @ai4life_harvard is gearing up for showcasing our recent research and connecting with the #ML #TrustworthyML #XAI community at #NeurIPS2022. Here’s where you can find us at a glance. More details about our papers/talks/panels in the thread below 👇 [1/N] Image
@ai4life_harvard [Conference Paper] Which Explanation Should I Choose? A Function Approximation Perspective to Characterizing Post Hoc Explanations (joint work with #TessaHan and @Suuraj) -- arxiv.org/abs/2206.01254. More details in this thread [2/N]
[Conference Paper] Efficient Training of Low-Curvature Neural Networks (joint work with @Suuraj, #KyleMatoba, @francoisfleuret) -- arxiv.org/abs/2206.07144. More details in this thread [3/N]
Read 10 tweets
𝙷𝚒𝚖𝚊 𝙻𝚊𝚔𝚔𝚊𝚛𝚊𝚓𝚞 Profile picture
Sep 18, 2022
One of the biggest criticisms of the field of post hoc #XAI is that each method "does its own thing", it is unclear how these methods relate to each other & which methods are effective under what conditions. Our #NeurIPS2022 paper provides (some) answers to these questions. [1/N]
In our #NeurIPS2022 paper, we unify eight different state-of-the-art local post hoc explanation methods, and show that they are all performing local linear approximations of the underlying models, albeit with different loss functions and notions of local neighborhoods. [2/N]
By doing so, we are able to explain the similarities & differences between these methods. These methods are similar in the sense that they all perform local linear approximations of models, but they differ considerably in "how" they perform these approximations [3/N]
Read 13 tweets
𝙷𝚒𝚖𝚊 𝙻𝚊𝚔𝚔𝚊𝚛𝚊𝚓𝚞 Profile picture
Jun 2, 2022
Explainable ML is a rather nascent field with lots of exciting work and discourse happening around it. But, it is very important to separate actual findings and results from hype. Below is a thread with some tips for navigating discourse and scholarship in explainable ML [1/N]
Overarching claims: We all have seen talks/tweets/discourse with snippets such as "explanations dont work" or "explanations are the answer to all these critical problems". When we hear such claims, they are often extrapolating results or findings from rather narrow studies. [2/N]
When we hear overarching claims, it is helpful to step back/ask what is the evidence to back such claims? which studies are such claims being based on? what is the context/application? how were the studies carried out? how reasonable is it to extrapolate these claims? [3/N]
Read 13 tweets
𝙷𝚒𝚖𝚊 𝙻𝚊𝚔𝚔𝚊𝚛𝚊𝚓𝚞 Profile picture
May 19, 2021
Excited to share our @AIESConf paper "Does Fair Ranking Improve Outcomes?: Understanding the Interplay of Human and Algorithmic Biases in Online Hiring". We investigate if fair ranking algorithms can mitigate gender biases in online hiring settings arxiv.org/pdf/2012.00423… [1/n]
More specifically, we were trying to examine the interplay between humans and fair ranking algorithms in online hiring settings, and assess if fair ranking algorithms can negate the effect of (any) gender biases prevalent in humans & ensure that the hiring outcomes are fair [2/n]
We found that fair ranking algorithms certainly help across all job contexts, but their effectiveness in mitigating gender biases (prevalent in online recruiters) heavily depends on the nature of the job. [3/n]
Read 8 tweets

Did Thread Reader help you today?

Support us! We are indie developers!

This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Don't want to be a Premium member but still want to support us?

Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us!

Send Email!

:(